└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # GAN-Inversion 2 | 3 | A collection of papers I am interested in. 4 | 5 | ## Awesome 6 | 7 | - https://ait.ethz.ch/index.php 8 | - https://liuyebin.com/student.html 9 | - https://virtualhumans.mpi-inf.mpg.de/ 10 | - https://ps.is.mpg.de/publications 11 | - https://www.mpi-inf.mpg.de/departments/visual-computing-and-artificial-intelligence/publications 12 | - https://ait.ethz.ch/people/hilliges/ 13 | - https://vlg.inf.ethz.ch/publications.html 14 | 15 | 16 | ## Renderer 17 | 18 | - https://github.com/eth-ait/aitviewer 19 | - https://github.com/mitsuba-renderer/mitsuba3 20 | - https://github.com/angeloskath/simple-3dviz 21 | - https://github.com/BachiLi/redner 22 | 23 | ## Pybind 24 | 25 | - https://github.com/pybind/cmake_example 26 | 27 | ## Video 28 | 29 | - https://github.com/mli/autocut 30 | 31 | 32 | 33 | ## Project 34 | 35 | - [mmgeneration](https://github.com/open-mmlab/mmgeneration) 36 | - [inr-gan](https://github.com/universome/inr-gan) 37 | - [ADA](https://github.com/NVlabs/stylegan2-ada-pytorch) 38 | - [awesome-image-translation](https://github.com/weihaox/awesome-image-translation) 39 | - [awesome-gan-inversion](https://github.com/weihaox/awesome-gan-inversion) 40 | - [naver-webtoon-faces](https://github.com/bryandlee/naver-webtoon-faces) 41 | - [GAN Experiments](http://www.nathanshipley.com/gan/#gan-015-toonify-layer-blending) 42 | - [timm](https://github.com/rwightman/pytorch-image-models) 43 | - [fun-with-computer-graphics](https://github.com/zheng95z/fun-with-computer-graphics) 44 | 45 | ### Face 46 | 47 | - [StyleGAN-nada](https://github.com/rinongal/StyleGAN-nada) 48 | - [RetrieveInStyle](https://github.com/mchong6/RetrieveInStyle) 49 | - [View_Neural_Talking_Head_Synthesis](https://github.com/zhanglonghao1992/One-Shot_Free-View_Neural_Talking_Head_Synthesis) 50 | - [Anime2Sketch](https://github.com/Mukosame/Anime2Sketch) 51 | 52 | ### 3D 53 | 54 | - [face3d](https://github.com/YadiraF/face3d) 55 | - [DECA](https://github.com/YadiraF/DECA) 56 | 57 | ### Tools 58 | 59 | - [bokeh](https://github.com/bokeh/bokeh) 60 | - [face-parsing.PyTorch](https://github.com/zllrunning/face-parsing.PyTorch) 61 | - [label-studio](https://github.com/heartexlabs/label-studio) 62 | - [streamlit-drawable-canvas](https://github.com/andfanilo/streamlit-drawable-canvas) 63 | - [face-alignment](https://github.com/1adrianb/face-alignment) 64 | - [remove images background](https://github.com/danielgatis/rembg) 65 | 66 | ### GUI 67 | 68 | - https://github.com/gradio-app/gradio 69 | 70 | ### StyleGAN 71 | 72 | - https://github.com/justinpinkney/awesome-pretrained-stylegan2 73 | - https://github.com/justinpinkney/awesome-pretrained-stylegan3 74 | - [generative-evaluation-prdc](https://github.com/clovaai/generative-evaluation-prdc) 75 | 76 | ### Style transfer 77 | 78 | - [style-transfer-pytorch](https://github.com/crowsonkb/style-transfer-pytorch) 79 | - [Stylebank-exp](https://github.com/PeterouZh/Stylebank-exp) 80 | 81 | ### Art 82 | 83 | - https://github.com/fogleman/primitive 84 | 85 | ### Anime 86 | 87 | - https://github.com/TachibanaYoshino/AnimeGAN 88 | - https://github.com/TachibanaYoshino/AnimeGANv2 89 | 90 | ## TOC 91 | 92 | - [To be read](#to-be-read) 93 | - [Disentanglement](#disentanglement) 94 | - [Inversion](#inversion) 95 | - [Encoder](#encoder) 96 | - [Survey](#survey) 97 | - [GANs](#gans) 98 | - [Style transfer](#style-transfer) 99 | - [Metric](#metric) 100 | - [Spectrum](#spectrum) 101 | - [Weakly Supervised Object Localization](#weakly-supervised-object-localization) 102 | - [NeRF](#nerf) 103 | - [3D](#3d) 104 | 105 | ## arXiv 106 | 107 | | Title | Venue | Code | Year | 108 | | :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------: | :-----------------------------------------------------------: | :--: | 109 | | [Perceptual Gradient Networks](http://arxiv.org/abs/2105.01957) | arXiv:2105.01957 [cs] | | 2021 | 110 | | [InfinityGAN: Towards Infinite-Resolution Image Synthesis](http://arxiv.org/abs/2104.03963) | arXiv:2104.03963 [cs] | | 2021 | 111 | | [Aliasing Is Your Ally: End-to-End Super-Resolution from Raw Image Bursts](http://arxiv.org/abs/2104.06191) | arXiv:2104.06191 [cs, eess] | | 2021 | 112 | | [StylePeople: A Generative Model of Fullbody Human Avatars](http://arxiv.org/abs/2104.08363) | arXiv:2104.08363 [cs] | | 2021 | 113 | | [Cross-Domain and Disentangled Face Manipulation with 3D Guidance](http://arxiv.org/abs/2104.11228) | arXiv:2104.11228 [cs] | | 2021 | 114 | | [On Buggy Resizing Libraries and Surprising Subtleties in FID Calculation](http://arxiv.org/abs/2104.11222) | arXiv:2104.11222 [cs] | | 2021 | 115 | | [FDA: Fourier Domain Adaptation for Semantic Segmentation](http://arxiv.org/abs/2004.05498) | arXiv:2004.05498 [cs] | [github](https://github.com/YanchaoYang/FDA) | 2020 | 116 | | [StyleMapGAN: Exploiting Spatial Dimensions of Latent in GAN for Real-Time Image Editing](http://arxiv.org/abs/2104.14754) | CVPR | | 2021 | 117 | | [Learning a Deep Reinforcement Learning Policy Over the Latent Space of a Pre-Trained GAN for Semantic Age Manipulation](http://arxiv.org/abs/2011.00954) | arXiv:2011.00954 [cs] | | 2021 | 118 | | [GANalyze: Toward Visual Definitions of Cognitive Image Properties](http://arxiv.org/abs/1906.10112) | arXiv:1906.10112 [cs] | | 2019 | 119 | | [On the “Steerability” of Generative Adversarial Networks](http://arxiv.org/abs/1907.07171) | arXiv:1907.07171 [cs] | | 2020 | 120 | | [Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation](http://arxiv.org/abs/2104.11116) | arXiv:2104.11116 [cs, eess] | | 2021 | 121 | | [Unsupervised Image-to-Image Translation via Pre-Trained StyleGAN2 Network](http://arxiv.org/abs/2010.05713) | arXiv:2010.05713 [cs] | [github](https://github.com/HideUnderBush/UI2I_via_StyleGAN2) | 2020 | 122 | | [DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort](http://arxiv.org/abs/2104.06490) | arXiv:2104.06490 [cs] | | 2021 | 123 | | [Anycost GANs for Interactive Image Synthesis and Editing](https://arxiv.org/abs/2103.03243v1) | CVPR | | 2021 | 124 | | [Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization](http://arxiv.org/abs/2104.05833) | arXiv:2104.05833 [cs] | | 2021 | 125 | | [Positional Encoding as Spatial Inductive Bias in GANs](http://arxiv.org/abs/2012.05217) | arXiv:2012.05217 [cs] | | 2020 | 126 | | [An Empirical Study of the Effects of Sample-Mixing Methods for Efficient Training of Generative Adversarial Networks](https://arxiv.org/abs/2104.03535v1) | arXiv:2104.03535 [cs.CV] | | 2021 | 127 | | [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://ieeexplore.ieee.org/document/9150840/) | CVPRW | [github](https://github.com/haofanwang/Score-CAM) | 2020 | 128 | | [Image Demoireing with Learnable Bandpass Filters](http://arxiv.org/abs/2004.00406) | arXiv:2004.00406 [cs] | | 2020 | 129 | | [Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization](http://arxiv.org/abs/2103.04523) | arXiv:2103.04523 [cs] | | 2021 | 130 | | [LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions](http://arxiv.org/abs/2104.00820) | arXiv:2104.00820 [cs] | | 2021 | 131 | | [Generating Images with Sparse Representations](http://arxiv.org/abs/2103.03841) | arXiv:2103.03841 [cs, stat] | | 2021 | 132 | | [PiCIE: Unsupervised Semantic Segmentation Using Invariance and Equivariance in Clustering](http://arxiv.org/abs/2103.17070) | CVPR | | 2021 | 133 | | [Dual Contrastive Loss and Attention for GANs](https://arxiv.org/abs/2103.16748v1) | arXiv:2103.16748 [cs.CV] | | 2021 | 134 | | [Unsupervised Disentanglement of Linear-Encoded Facial Semantics](https://arxiv.org/abs/2103.16605v1) | CVPR | | 2021 | 135 | | [Emergence of Object Segmentation in Perturbed Generative Models](http://arxiv.org/abs/1905.12663) | arXiv:1905.12663 [cs] | [github](https://github.com/adambielski/perturbed-seg) | 2019 | 136 | | [Unsupervised Discovery of DisentangledManifolds in GANs](http://arxiv.org/abs/2011.11842) | arXiv:2011.11842 [cs] | [github](https://github.com/anvoynov/GANLatentDiscovery) | 2020 | 137 | | [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](http://arxiv.org/abs/2103.17249) | arXiv:2103.17249 [cs] | [github](https://github.com/orpatashnik/StyleCLIP) | 2021 | 138 | | [Few-Shot Semantic Image Synthesis Using StyleGAN Prior](http://arxiv.org/abs/2103.14877) | arXiv:2103.14877 [cs] | | 2021 | 139 | 140 | ## Disentanglement 141 | 142 | | Title | Venue | Code | Year | 143 | | :------------------------------------------------------------------------------------------------------------------------- | :-------------------: | :--------------------------------------------------------: | :--: | 144 | | [GANSpace: Discovering Interpretable GAN Controls](http://arxiv.org/abs/2004.02546) | arXiv:2004.02546 [cs] | [GANSpace](https://github.com/harskish/ganspace) | 2020 | 145 | | [Interpreting the Latent Space of GANs for Semantic Face Editing](http://arxiv.org/abs/1907.10786) | CVPR | [InterFaceGAN](https://github.com/genforce/interfacegan) | 2020 | 146 | | [Closed-Form Factorization of Latent Semantics in GANs](http://arxiv.org/abs/2007.06600) | arXiv:2007.06600 [cs] | [sefa](https://github.com/genforce/sefa) | 2020 | 147 | | [StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation](http://arxiv.org/abs/2011.12799) | arXiv:2011.12799 [cs] | [StyleSpace](https://github.com/xrenaa/StyleSpace-pytorch) | 2020 | 148 | | [Unsupervised Image Transformation Learning via Generative Adversarial Networks](http://arxiv.org/abs/2103.07751) | arXiv:2103.07751 [cs] | [github](https://github.com/genforce/trgan) | 2021 | 149 | | [Resolution Dependent GAN Interpolation for Controllable Image Synthesis Between Domains](http://arxiv.org/abs/2010.05334) | arXiv:2010.05334 [cs] | [toonify](https://github.com/justinpinkney/toonify) | 2020 | 150 | | [WarpedGANSpace: Finding Non-Linear RBF Paths in GAN Latent Space](http://arxiv.org/abs/2109.13357) | arXiv:2109.13357 [cs] | | 2021 | 151 | | [Discovering Interpretable Latent Space Directions of GANs beyond Binary Attributes] CVPR | | 2021 | 152 | 153 | ### Semantic hierarchy 154 | 155 | | Title | Venue | Code | Year | 156 | | :------------------------------------------------------------------------------------------------------------------- | :-------------------: | :--: | :--: | 157 | | [Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis](http://arxiv.org/abs/1911.09267) | arXiv:1911.09267 [cs] | | 2020 | 158 | 159 | ## Inversion 160 | 161 | ### Optimization 162 | 163 | | Title | Venue | Code | Year | 164 | | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------------------------: | :------------------------------------------------------------------: | :--: | 165 | | [Image2StyleGAN++: How to Edit the Embedded Images?](http://arxiv.org/abs/1911.11544) | arXiv:1911.11544 [cs] | | 2020 | 166 | | [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](http://arxiv.org/abs/1904.03189) | ICCV | | 2019 | 167 | | [Inverting The Generator Of A Generative Adversarial Network](http://arxiv.org/abs/1611.05644) | arXiv:1611.05644 [cs] | | 2016 | 168 | | [Feature-Based Metrics for Exploring the Latent Space of Generative Models](https://openreview.net/forum?id=BJslDBkwG) | ICLRW | | 2018 | 169 | | [Understanding Deep Image Representations by Inverting Them](http://arxiv.org/abs/1412.0035) | CVPR | | 2015 | 170 | | [Dreaming to Distill: Data-Free Knowledge Transfer via DeepInversion](http://arxiv.org/abs/1912.08795) | arXiv:1912.08795 [cs, stat] | [DeepInversion](https://github.com/NVlabs/DeepInversion) | 2020 | 171 | | [IMAGINE: Image Synthesis by Image-Guided Model Inversion](http://arxiv.org/abs/2104.05895) | arXiv:2104.05895 [cs] | | 2021 | 172 | | [Image Processing Using Multi-Code GAN Prior](http://arxiv.org/abs/1912.07116) | CVPR | [mGANprior](https://github.com/genforce/mganprior) | 2020 | 173 | | [Generative Visual Manipulation on the Natural Image Manifold](http://arxiv.org/abs/1609.03552) | ECCV | | 2018 | 174 | | [GAN Dissection: Visualizing and Understanding Generative Adversarial Networks](http://arxiv.org/abs/1811.10597) | arXiv:1811.10597 [cs] | | 2018 | 175 | | [GAN-Based Projector for Faster Recovery with Convergence Guarantees in Linear Inverse Problems](http://arxiv.org/abs/1902.09698) | arXiv:1902.09698 [cs, eess, stat] | | 2019 | 176 | | [Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models](http://openaccess.thecvf.com/content_CVPR_2020/html/Daras_Your_Local_GAN_Designing_Two_Dimensional_Local_Attention_Mechanisms_for_CVPR_2020_paper.html) | CVPR | | 2020 | 177 | | [Rewriting a Deep Generative Model](http://arxiv.org/abs/2007.15646) | arXiv:2007.15646 [cs] | | 2020 | 178 | | [Transforming and Projecting Images into Class-Conditional Generative Networks](http://arxiv.org/abs/2005.01703) | arXiv:2005.01703 [cs] | | 2020 | 179 | | [StyleGAN2 Distillation for Feed-Forward Image Manipulation](https://arxiv.org/abs/2003.03581v2) | arXiv:2003.03581 [cs.CV] | | 2020 | 180 | | [On the “Steerability” of Generative Adversarial Networks](http://arxiv.org/abs/1907.07171) | arXiv:1907.07171 [cs] | | 2020 | 181 | | [Unsupervised Discovery of DisentangledManifolds in GANs](http://arxiv.org/abs/2011.11842) | arXiv:2011.11842 [cs] | | 2020 | 182 | | [PIE: Portrait Image Embedding for Semantic Control](http://arxiv.org/abs/2009.09485) | arXiv:2009.09485 [cs] | | 2020 | 183 | | [GANSpace: Discovering Interpretable GAN Controls](http://arxiv.org/abs/2004.02546) | NeurIPS | | 2020 | 184 | | [When and How Can Deep Generative Models Be Inverted?](http://arxiv.org/abs/2006.15555) | arXiv:2006.15555 [cs, stat] | | 2020 | 185 | | [Style Intervention: How to Achieve Spatial Disentanglement with Style-Based Generators?](http://arxiv.org/abs/2011.09699) | arXiv:2011.09699 [cs] | | 2020 | 186 | | [StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation](http://arxiv.org/abs/2011.12799) | arXiv:2011.12799 [cs] | | 2020 | 187 | | [Navigating the GAN Parameter Space for Semantic Image Editing](http://arxiv.org/abs/2011.13786) | arXiv:2011.13786 [cs] | | 2021 | 188 | | [Mask-Guided Discovery of Semantic Manifolds in Generative Models](http://arxiv.org/abs/2105.07273) | arXiv:2105.07273 [cs] | [masked-gan-manifold](https://github.com/bmolab/masked-gan-manifold) | 2021 | 189 | | [StyleFlow: Attribute-Conditioned Exploration of StyleGAN-Generated Images Using Conditional Continuous Normalizing Flows](http://arxiv.org/abs/2008.02401) | arXiv:2008.02401 [cs] | [StyleFlow](https://github.com/RameenAbdal/StyleFlow) | 2020 | 190 | | [Disentangled Face Attribute Editing via Instance-Aware Latent Space Search](http://arxiv.org/abs/2105.12660) | arXiv:2105.12660 [cs] | | 2021 | 191 | | [Barbershop: GAN-Based Image Compositing Using Segmentation Masks](http://arxiv.org/abs/2106.01505) | arXiv:2106.01505 [cs] | | 2021 | 192 | | [Unsupervised Discovery of Interpretable Directions in the GAN Latent Space](http://arxiv.org/abs/2002.03754) | arXiv:2002.03754 [cs, stat] | [GANLatentDiscovery](https://github.com/anvoynov/GANLatentDiscovery) | 2020 | 193 | | [Pivotal Tuning for Latent-Based Editing of Real Images](http://arxiv.org/abs/2106.05744) | arXiv:2106.05744 [cs] | [PTI](https://github.com/danielroich/PTI) | 2021 | 194 | | [Editing in Style: Uncovering the Local Semantics of GANs](http://arxiv.org/abs/2004.14367) | CVPR | | 2020 | 195 | | [Retrieve in Style: Unsupervised Facial Feature Transfer and Retrieval](http://arxiv.org/abs/2107.06256) | arXiv:2107.06256 [cs] | [RetrieveInStyle](https://github.com/mchong6/RetrieveInStyle) | 2021 | 196 | | [StyleCariGAN: Caricature Generation via StyleGAN Feature Map Modulation](http://arxiv.org/abs/2107.04331) | arXiv:2107.04331 [cs] | | 2021 | 197 | | [A Simple Baseline for StyleGAN Inversion](http://arxiv.org/abs/2104.07661) | arXiv:2104.07661 [cs] | | 2021 | 198 | | [From Continuity to Editability: Inverting GANs with Consecutive Images](http://arxiv.org/abs/2107.13812) | arXiv:2107.13812 [cs] | | 2021 | 199 | | [AgileGAN: Stylizing Portraits by Inversion-Consistent Transfer Learning]() | ACM Transactions on Graphics (Proc. SIGGRAPH) | | 2021 | 200 | | [Talk-to-Edit: Fine-Grained Facial Editing via Dialog](http://arxiv.org/abs/2109.04425) | ICCV | [Talk-to-Edit](https://github.com/yumingj/Talk-to-Edit) | 2021 | 201 | | [Improved StyleGAN Embedding: Where Are the Good Latents?](http://arxiv.org/abs/2012.09036) | arXiv:2012.09036 [cs] | [II2S](https://github.com/ZPdesu/II2S) | 2021 | 202 | | [EditGAN: High-Precision Semantic Image Editing](https://arxiv.org/abs/2111.03186v1) | | [editGAN_release](https://github.com/nv-tlabs/editGAN_release) | 2021 | 203 | | [Grasping the Arrow of Time from the Singularity: Decoding Micromotion in Low-Dimensional Latent Spaces from StyleGAN](http://arxiv.org/abs/2204.12696) | arXiv:2204.12696 [cs] | | 2022 | 204 | | [Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing](http://arxiv.org/abs/2206.08357) | CVPR | [sam_inversion](https://github.com/adobe-research/sam_inversion) | arXiv. 2022 | 205 | | [Real Image Inversion via Segments](http://arxiv.org/abs/2110.06269) | arXiv:2110.06269 | [Chunkmogrify](https://github.com/futscdav/Chunkmogrify) | 2021 | 206 | 207 | 208 | ### Encoder 209 | 210 | | Title | Venue | Code | Year | 211 | | :----------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------: | :------------------------------------------------------------------: | :--: | 212 | | [GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution](http://arxiv.org/abs/2012.00739) | arXiv:2012.00739 [cs] | [GLEAN]() | 2020 | 213 | | [Swapping Autoencoder for Deep Image Manipulation](http://arxiv.org/abs/2007.00653) | arXiv:2007.00653 [cs] | [github](https://github.com/rosinality/swapping-autoencoder-pytorch) | 2020 | 214 | | [In-Domain GAN Inversion for Real Image Editing](http://arxiv.org/abs/2004.00049) | ECCV | | 2020 | 215 | | [ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement](http://arxiv.org/abs/2104.02699) | arXiv:2104.02699 [cs] | [ReStyle](https://github.com/yuval-alaluf/restyle-encoder) | 2021 | 216 | | [Interpreting the Latent Space of GANs for Semantic Face Editing](http://arxiv.org/abs/1907.10786) | CVPR | | 2020 | 217 | | [Face Identity Disentanglement via Latent Space Mapping](http://arxiv.org/abs/2005.07728) | arXiv:2005.07728 [cs] | | 2020 | 218 | | [Collaborative Learning for Faster StyleGAN Embedding](http://arxiv.org/abs/2007.01758) | arXiv:2007.01758 [cs] | | 2020 | 219 | | [Unsupervised Discovery of DisentangledManifolds in GANs](http://arxiv.org/abs/2011.11842) | arXiv:2011.11842 [cs] | | 2020 | 220 | | [Generative Hierarchical Features from Synthesizing Images](http://arxiv.org/abs/2007.10379) | arXiv:2007.10379 [cs] | | 2020 | 221 | | [One Shot Face Swapping on Megapixels](http://arxiv.org/abs/2105.04932) | arXiv:2105.04932 [cs] | | 2021 | 222 | | [GAN Prior Embedded Network for Blind Face Restoration in the Wild](https://arxiv.org/abs/2105.06070v1) | 2021 | 223 | | [Adversarial Latent Autoencoders](http://openaccess.thecvf.com/content_CVPR_2020/html/Pidhorskyi_Adversarial_Latent_Autoencoders_CVPR_2020_paper.html) | CVPR | [ALAE](https://github.com/podgorskiy/ALAE) | 2020 | 224 | | [Encoding in Style: A StyleGAN Encoder for Image-to-Image Translation](http://arxiv.org/abs/2008.00951) | arXiv:2008.00951 [cs] | [psp](https://github.com/eladrich/pixel2style2pixel) | 2021 | 225 | | [Designing an Encoder for StyleGAN Image Manipulation](http://arxiv.org/abs/2102.02766) | arXiv:2102.02766 [cs] | [encoder4editing](https://github.com/omertov/encoder4editing) | 2021 | 226 | | [A Latent Transformer for Disentangled and Identity-Preserving Face Editing](http://arxiv.org/abs/2106.11895) | arXiv:2106.11895 [cs] | | 2021 | 227 | | [ShapeEditer: A StyleGAN Encoder for Face Swapping](http://arxiv.org/abs/2106.13984) | arXiv:2106.13984 [cs] | | 2021 | 228 | | [Force-in-Domain GAN Inversion](http://arxiv.org/abs/2107.06050) | arXiv:2107.06050 [cs, eess] | | 2021 | 229 | | [StyleFusion: A Generative Model for Disentangling Spatial Segments](http://arxiv.org/abs/2107.07437) | arXiv:2107.07437 [cs] | | 2021 | 230 | | [Perceptually Validated Precise Local Editing for Facial Action Units with StyleGAN](http://arxiv.org/abs/2107.12143) | arXiv:2107.12143 [cs] | | 2021 | 231 | | [StyleGAN2 Distillation for Feed-Forward Image Manipulation](https://arxiv.org/abs/2003.03581v2) | arXiv:2003.03581 [cs.CV] | | 2020 | 232 | | [GAN Inversion for Out-of-Range Images with Geometric Transformations](http://arxiv.org/abs/2108.08998) | ICCV | | 2021 | 233 | | :heart: [DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing](http://arxiv.org/abs/2109.10737) | arXiv:2109.10737 [cs] | [DyStyle](https://github.com/phycvgan/DyStyle) | 2021 | 234 | | [High-Fidelity GAN Inversion for Image Attribute Editing](http://arxiv.org/abs/2109.06590) | arXiv:2109.06590 [cs] | | 2021 | 235 | | :heart: [Few-Shot Knowledge Transfer for Fine-Grained Cartoon Face Generation](http://arxiv.org/abs/2007.13332) | arXiv:2007.13332 [cs] | | 2020 | 236 | | :heart: [HyperInverter: Improving StyleGAN Inversion via Hypernetwork](http://arxiv.org/abs/2112.00719) | CVPR | [HyperInverter](https://github.com/VinAIResearch/HyperInverter) | arXiv. 2022 | 237 | | [High-Fidelity GAN Inversion with Padding Space] | ECCV | [padinv](https://github.com/EzioBy/padinv) | 2022 | 238 | 239 | 240 | ### Hybrid optimization 241 | 242 | | Title | Venue | Code | Year | 243 | | :---------------------------------------------------------------------------------------------- | :--------------------------: | :--: | :--: | 244 | | [Generative Visual Manipulation on the Natural Image Manifold](http://arxiv.org/abs/1609.03552) | ECCV | | 2018 | 245 | | [Semantic Photo Manipulation with a Generative Image Prior](https://arxiv.org/abs/2005.07727) | ACM Transactions on Graphics | | 2019 | 246 | | [Seeing What a GAN Cannot Generate](http://arxiv.org/abs/1910.11626) | arXiv:1910.11626 [cs, eess] | | 2019 | 247 | | [In-Domain GAN Inversion for Real Image Editing](http://arxiv.org/abs/2004.00049) | ECCV | | 2020 | 248 | 249 | ### Without optimization 250 | 251 | | Title | Venue | Code | Year | 252 | | :------------------------------------------------------------------------------------------------------------------------- | :-------------------: | :--------------------------------------: | :--: | 253 | | [Closed-Form Factorization of Latent Semantics in GANs](http://arxiv.org/abs/2007.06600) | arXiv:2007.06600 [cs] | | 2020 | 254 | | [GAN “Steerability” without Optimization](http://arxiv.org/abs/2012.05328) | arXiv:2012.05328 [cs] | | 2021 | 255 | | [Low-Rank Subspaces in GANs](http://arxiv.org/abs/2106.04488) | arXiv:2106.04488 [cs] | | 2021 | 256 | | [LARGE: Latent-Based Regression through GAN Semantics](http://arxiv.org/abs/2107.11186) | arXiv:2107.11186 [cs] | | 2021 | 257 | | [Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation](http://arxiv.org/abs/2108.07668) | ICCV | | 2021 | 258 | | [Controllable and Compositional Generation with Latent-Space Energy-Based Models](http://arxiv.org/abs/2110.10873) | NeurIPS | [LACE](https://github.com/NVlabs/LACE) | 2021 | 259 | | [Do Generative Models Know Disentanglement? Contrastive Learning Is All You Need](http://arxiv.org/abs/2102.10543) | arXiv:2102.10543 [cs] | [DisCo](https://github.com/xrenaa/DisCo) | 2021 | 260 | 261 | ### DGP 262 | 263 | | Title | Venue | Code | Year | 264 | | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | :--------------------------: | :--------------------------------------------------------------------------------------: | :--: | 265 | | :heavy_check_mark: [Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation](http://arxiv.org/abs/2003.13659) | ECCV | [DGP](https://github.com/XingangPan/deep-generative-prior) | 2020 | 266 | | :heavy_check_mark: [PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models](http://openaccess.thecvf.com/content_CVPR_2020/html/Menon_PULSE_Self-Supervised_Photo_Upsampling_via_Latent_Space_Exploration_of_Generative_CVPR_2020_paper.html) | CVPR | [PULSE]() | 2020 | 267 | | :heavy_check_mark: [GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution](http://arxiv.org/abs/2012.00739) | arXiv:2012.00739 [cs] | | 2020 | 268 | | [Unsupervised Portrait Shadow Removal via Generative Priors](http://arxiv.org/abs/2108.03466) | arXiv:2108.03466 [cs] | | 2021 | 269 | | [Towards Real-World Blind Face Restoration with Generative Facial Prior](http://arxiv.org/abs/2101.04061) | CVPR | [GFPGAN](https://github.com/TencentARC/GFPGAN) | 2021 | 270 | | [Towards Vivid and Diverse Image Colorization with Generative Color Prior](http://arxiv.org/abs/2108.08826) | ICCV | | 2021 | 271 | | [Self-Validation: Early Stopping for Single-Instance Deep Generative Priors]() | arXiv:2110.12271 [cs.CV] | | 2021 | 272 | | [One-Shot Generative Domain Adaptation](http://arxiv.org/abs/2111.09876) | arXiv:2111.09876 [cs] | | 2021 | 273 | | :heart: [Time-Travel Rephotography]() | ACM Transactions on Graphics | [code](https://github.com/Time-Travel-Rephotography/Time-Travel-Rephotography.github.io) | 2021 | 274 | 275 | ### Cls 276 | 277 | | Title | Venue | Code | Year | 278 | | :---------------------------------------------------------------------------------------------------------------------- | :-------------------: | :--: | :--: | 279 | | [Contrastive Model Inversion for Data-Free Knowledge Distillation](http://arxiv.org/abs/2105.08584) | arXiv:2105.08584 [cs] | | 2021 | 280 | | [Generative Models as a Data Source for Multiview Representation Learning](http://arxiv.org/abs/2106.05258) | arXiv:2106.05258 [cs] | | 2021 | 281 | | [Inverting and Understanding Object Detectors](http://arxiv.org/abs/2106.13933) | arXiv:2106.13933 [cs] | | 2021 | 282 | | [Deep Neural Networks Are Surprisingly Reversible: A Baseline for Zero-Shot Inversion](http://arxiv.org/abs/2107.06304) | arXiv:2107.06304 [cs] | | 2021 | 283 | | [Ensembling with Deep Generative Views](http://arxiv.org/abs/2104.14551) | arXiv:2104.14551 [cs] | | 2021 | 284 | 285 | ### Change pose implicitly 286 | 287 | | Title | Venue | Code | Year | 288 | | :------------------------------------------------------------------------------------------------------------------- | :-------------------: | :----------------------------------------------: | :--: | 289 | | [On the “Steerability” of Generative Adversarial Networks](http://arxiv.org/abs/1907.07171) | arXiv:1907.07171 [cs] | | 2020 | 290 | | [Interpreting the Latent Space of GANs for Semantic Face Editing](http://arxiv.org/abs/1907.10786) | CVPR | | 2020 | 291 | | [GANSpace: Discovering Interpretable GAN Controls](http://arxiv.org/abs/2004.02546) | arXiv:2004.02546 [cs] | [GANSpace](https://github.com/harskish/ganspace) | 2020 | 292 | | [Closed-Form Factorization of Latent Semantics in GANs](http://arxiv.org/abs/2007.06600) | arXiv:2007.06600 [cs] | [sefa](https://github.com/genforce/sefa) | 2020 | 293 | | [StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGAN](http://arxiv.org/abs/2111.01619) | arXiv:2111.01619 [cs] | | 2021 | 294 | | [Using Latent Space Regression to Analyze and Leverage Compositionality in GANs](https://arxiv.org/abs/2103.10426v1) | ICLR | | 2021 | 295 | 296 | ## Survey 297 | 298 | | Title | Venue | Code | Year | 299 | | :--------------------------------------------------------- | :-------------------: | :--: | :--: | 300 | | [GAN Inversion: A Survey](http://arxiv.org/abs/2101.05278) | arXiv:2101.05278 [cs] | | 2021 | 301 | 302 | ## GANs 303 | 304 | ### NeurIPS 2021 305 | 306 | | Title | Venue | Code | Year | 307 | | :------------------------------------------------------------------------------------------------- | :-----: | :--: | :--: | 308 | | [Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training](http://arxiv.org/abs/2111.01118) | NeurIPS | | 2021 | 309 | 310 | ### Theory 311 | 312 | | Title | Venue | Code | Year | 313 | | :---------------------------------------------------------------------------------------------------------- | :-------------------------------: | :--: | :--: | 314 | | :white_check_mark: [Towards a Better Global Loss Landscape of GANs](http://arxiv.org/abs/2011.04926) | NeurIPS | | 2020 | 315 | | [On the Benefit of Width for Neural Networks: Disappearance of Bad Basins](http://arxiv.org/abs/1812.11039) | arXiv:1812.11039 [cs, math, stat] | | 2021 | 316 | 317 | ### Regs 318 | 319 | | Title | Venue | Code | Year | 320 | | :---------------------------------------------------------------------------------------------------- | :---: | :--: | :--: | 321 | | [The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement](http://arxiv.org/abs/2008.10599) | ECCV | | 2020 | 322 | 323 | ### Detection 324 | 325 | | Title | Venue | Code | Year | 326 | | :------------------------------------------------------------------------------------------------- | :-------------------: | :--: | :--: | 327 | | [Self-Supervised Object Detection via Generative Image Synthesis](http://arxiv.org/abs/2110.09848) | arXiv:2110.09848 [cs] | | 2021 | 328 | 329 | ### StyleGANs 330 | 331 | | Title | Venue | Code | Year | 332 | | :------------------------------------------------------------------------------------------------------------------------------------------------------ | :-------------------------------: | :--------------------------------------------------------------------------------------------------------------: | :--: | 333 | | [A Style-Based Generator Architecture for Generative Adversarial Networks](http://arxiv.org/abs/1812.04948) | CVPR | | 2019 | 334 | | [Analyzing and Improving the Image Quality of StyleGAN](http://arxiv.org/abs/1912.04958) | arXiv:1912.04958 [cs, eess, stat] | | 2019 | 335 | | [Training Generative Adversarial Networks with Limited Data](http://arxiv.org/abs/2006.06676) | arXiv:2006.06676 [cs, stat] | | 2020 | 336 | | [Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data](https://openreview.net/forum?id=spjlJ4jeM_) | NeurIPS | | 2021 | 337 | | [Alias-Free Generative Adversarial Networks](http://arxiv.org/abs/2106.12423) | arXiv:2106.12423 [cs, stat] | [alias-free-gan](https://github.com/NVlabs/alias-free-gan), [rep2](https://github.com/duskvirkus/alias-free-gan) | 2021 | 338 | | [Transforming the Latent Space of StyleGAN for Real Face Editing](http://arxiv.org/abs/2105.14230) | arXiv:2105.14230 [cs] | [TransStyleGAN](https://github.com/AnonSubm2021/TransStyleGAN) | 2021 | 339 | | [MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis](http://arxiv.org/abs/2104.04767) | arXiv:2104.04767 [cs, eess] | [MobileStyleGAN](https://github.com/bes-dev/MobileStyleGAN.pytorch) | 2021 | 340 | | [Few-Shot Image Generation via Cross-Domain Correspondence](http://arxiv.org/abs/2104.06820) | CVPR | [few-shot-gan-adaptation](https://github.com/utkarshojha/few-shot-gan-adaptation) | 2021 | 341 | | [EigenGAN: Layer-Wise Eigen-Learning for GANs](http://arxiv.org/abs/2104.12476) | arXiv:2104.12476 [cs, stat] | [EigenGAN](https://github.com/LynnHo/EigenGAN-Tensorflow) | 2021 | 342 | | :heart: [Toward Spatially Unbiased Generative Models](http://arxiv.org/abs/2108.01285) | ICCV | [toward_spatial_unbiased](https://github.com/jychoi118/toward_spatial_unbiased) | 2021 | 343 | | [Interpreting Generative Adversarial Networks for Interactive Image Generation](http://arxiv.org/abs/2108.04896) | arXiv:2108.04896 [cs] | | 2021 | 344 | | [Explaining in Style: Training a GAN to Explain a Classifier in StyleSpace](http://arxiv.org/abs/2104.13369) | ICCV | [explaining-in-style](https://github.com/google/explaining-in-style) | 2021 | 345 | | :white_check_mark: [Projected GANs Converge Faster]() | NeurIPS | [projected_gan](https://github.com/autonomousvision/projected_gan) | 2021 | 346 | | :white_check_mark: [Towards Faster and Stabilized GAN Training for High-Fidelity Few-Shot Image Synthesis](https://openreview.net/forum?id=1Fqg133qRaI) | ICLR2021 | [github](https://github.com/lucidrains/lightweight-gan) | 2021 | 347 | | :heart: [Ensembling Off-the-Shelf Models for GAN Training](http://arxiv.org/abs/2112.09130) | arXiv:2112.09130 [cs] | [vision-aided-gan](https://github.com/nupurkmr9/vision-aided-gan) | 2021 | 348 | | :heart: [StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets](http://arxiv.org/abs/2202.00273) | arXiv:2202.00273 [cs] | | 2022 | 349 | | [When, Why, and Which Pretrained GANs Are Useful?](http://arxiv.org/abs/2202.08937) | ICLR | | 2022 | 350 | | [A U-Net Based Discriminator for Generative Adversarial Networks](http://arxiv.org/abs/2002.12655) | CVPR | | 2020 | 351 | 352 | ### Transformer 353 | 354 | | Title | Venue | Code | Year | 355 | | :------------------------------------------------------------------------------------------------------- | :-------------------: | :--------------------------------------------------: | :--: | 356 | | [Compositional Transformers for Scene Generation](http://arxiv.org/abs/2111.08960) | NeurIPS | | 2021 | 357 | | :heart: [GAN-Supervised Dense Visual Alignment](http://arxiv.org/abs/2112.05143) | arXiv:2112.05143 [cs] | [gangealing](https://github.com/wpeebles/gangealing) | 2021 | 358 | | [Improved Transformer for High-Resolution GANs](http://arxiv.org/abs/2106.07631) | arXiv:2106.07631 [cs] | | 2021 | 359 | | [MaskGIT: Masked Generative Image Transformer](http://arxiv.org/abs/2202.04200) | arXiv:2202.04200 [cs] | | 2022 | 360 | | [StyleSwin: Transformer-Based GAN for High-Resolution Image Generation](http://arxiv.org/abs/2112.10762) | CVPR | | 2022 | 361 | 362 | ### SinGAN 363 | 364 | | Title | Venue | Code | Year | 365 | | :-------------------------------------------------------------------------------------------------------- | :-------------------: | :--: | :--: | 366 | | [ExSinGAN: Learning an Explainable Generative Model from a Single Image](http://arxiv.org/abs/2105.07350) | arXiv:2105.07350 [cs] | | 2021 | 367 | 368 | ### Video 369 | 370 | | Title | Venue | Code | Year | 371 | | :---------------------------------------------------------------------------------------------- | :-------------------: | :--: | :--: | 372 | | :heart: [Diverse Generation from a Single Video Made Possible](http://arxiv.org/abs/2109.08591) | arXiv:2109.08591 [cs] | | 2021 | 373 | 374 | ### GANs 375 | 376 | | Title | Venue | Code | Year | 377 | | :-------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------: | :--------------------------------------------------: | :--: | 378 | | :white_check_mark: [Differentiable Augmentation for Data-Efficient GAN Training](http://arxiv.org/abs/2006.10738) | arXiv:2006.10738 [cs] | | 2020 | 379 | | [Sampling Generative Networks](http://arxiv.org/abs/1609.04468) | arXiv:1609.04468 [cs, stat] | | 2016 | 380 | | [Combining Transformer Generators with Convolutional Discriminators](http://arxiv.org/abs/2105.10189) | arXiv:2105.10189 [cs] | | 2021 | 381 | | [Improving Generation and Evaluation of Visual Stories via Semantic Consistency](http://arxiv.org/abs/2105.10026) | arXiv:2105.10026 [cs] | | 2021 | 382 | | [TediGAN: Text-Guided Diverse Face Image Generation and Manipulation](http://arxiv.org/abs/2012.03308) | CVPR | | 2021 | 383 | | [Data-Efficient Instance Generation from Instance Discrimination](http://arxiv.org/abs/2106.04566) | arXiv:2106.04566 [cs] | | 2021 | 384 | | [Styleformer: Transformer Based Generative Adversarial Networks with Style Vector](http://arxiv.org/abs/2106.07023) | arXiv:2106.07023 [cs, eess] | | 2021 | 385 | | [FBC-GAN: Diverse and Flexible Image Synthesis via Foreground-Background Composition](http://arxiv.org/abs/2107.03166) | arXiv:2107.03166 [cs] | | 2021 | 386 | | [ViTGAN: Training GANs with Vision Transformers](http://arxiv.org/abs/2107.04589) | arXiv:2107.04589 [cs, eess] | | 2021 | 387 | | [Learning Efficient GANs for Image Translation via Differentiable Masks and Co-Attention Distillation](http://arxiv.org/abs/2011.08382) | arXiv:2011.08382 [cs] | | 2021 | 388 | | [CGANs with Auxiliary Discriminative Classifier](http://arxiv.org/abs/2107.10060) | arXiv:2107.10060 [cs] | | 2021 | 389 | | [A Good Image Generator Is What You Need for High-Resolution Video Synthesis](http://arxiv.org/abs/2104.15069) | ICLR | | 2021 | 390 | | [Dual Projection Generative Adversarial Networks for Conditional Image Generation](http://arxiv.org/abs/2108.09016) | ICCV | | 2021 | 391 | | [Your GAN Is Secretly an Energy-Based Model and You Should Use Discriminator Driven Latent Sampling](http://arxiv.org/abs/2003.06060) | arXiv:2003.06060 [cs, stat] | [CGAN-DDLS](https://github.com/JHpark1677/CGAN-DDLS) | 2021 | 392 | | [Manifold-Preserved GANs](http://arxiv.org/abs/2109.08955) | arXiv:2109.08955 [cs] | | 2021 | 393 | | [Latent Reweighting, an Almost Free Improvement for GANs](http://arxiv.org/abs/2110.09803) | arXiv:2110.09803 [cs] | | 2021 | 394 | | [STRANSGAN: AN EMPIRICAL STUDY ON TRANS- FORMER IN GANS]() | arXiv:2110.13107 [cs.CV] | | 2021 | 395 | | [Self-Supervised GANs with Label Augmentation](http://arxiv.org/abs/2106.08601) | arXiv:2106.08601 [cs] | | 2021 | 396 | | [Regularizing Generative Adversarial Networks under Limited Data](http://arxiv.org/abs/2104.03310) | CVPR | [github](https://github.com/PeterouZh/lecam-gan) | 2021 | 397 | 398 | ### cGANs 399 | 400 | | Title | Venue | Code | Year | 401 | | :------------------------------------------------------------------------------ | :-------------------------: | :--: | :--: | 402 | | [Unbiased Auxiliary Classifier GANs with MINE](http://arxiv.org/abs/2006.07567) | arXiv:2006.07567 [cs] | | 2020 | 403 | | [Twin Auxiliary Classifiers GAN](http://arxiv.org/abs/1907.02690) | arXiv:1907.02690 [cs, stat] | | 2019 | 404 | 405 | ### Finetune 406 | 407 | | Title | Venue | Code | Year | 408 | | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------: | :-----------------------------------------------------------------: | :--: | 409 | | FreezeG | | [github](https://github.com/bryandlee/FreezeG) | | 410 | | :white_check_mark: [Freeze the Discriminator: A Simple Baseline for Fine-Tuning GANs](http://arxiv.org/abs/2002.10964) | arXiv:2002.10964 [cs, stat] | [FreezeD](https://github.com/sangwoomo/FreezeD) | 2020 | 411 | | [Fine-Tuning StyleGAN2 For Cartoon Face Generation](http://arxiv.org/abs/2106.12445) | arXiv:2106.12445 [cs, eess] | [Cartoon-StyleGAN](https://github.com/happy-jihye/Cartoon-StyleGAN) | 2021 | 412 | | [Transferring GANs: Generating Images from Limited Data](http://arxiv.org/abs/1805.01677) | ECCV | | 2018 | 413 | | [Image Generation From Small Datasets via Batch Statistics Adaptation](http://arxiv.org/abs/1904.01774) | ICCV | | 2019 | 414 | | [MineGAN: Effective Knowledge Transfer From GANs to Target Domains With Few Images](http://openaccess.thecvf.com/content_CVPR_2020/html/Wang_MineGAN_Effective_Knowledge_Transfer_From_GANs_to_Target_Domains_With_CVPR_2020_paper.html) | CVPR | | 2020 | 415 | 416 | ### Compression 417 | 418 | | Title | Venue | Code | Year | 419 | | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------: | :---------------------------------: | :--: | 420 | | [GAN Compression: Efficient Architectures for Interactive Conditional GANs](http://openaccess.thecvf.com/content_CVPR_2020/html/Li_GAN_Compression_Efficient_Architectures_for_Interactive_Conditional_GANs_CVPR_2020_paper.html) | CVPR | | 2020 | 421 | | [Online Multi-Granularity Distillation for GAN Compression](http://arxiv.org/abs/2108.06908) | ICCV | | 2021 | 422 | | [Revisiting Discriminator in GAN Compression: A Generator-Discriminator Cooperative Compression Scheme](http://arxiv.org/abs/2110.14439) | arXiv:2110.14439 [cs] | [GCC](https://github.com/SJLeo/GCC) | 2021 | 423 | 424 | ### Detection fake 425 | 426 | | Title | Venue | Code | Year | 427 | | :------------------------------------------------------------------------------------------------------- | :-------------------: | :--: | :--: | 428 | | [Robust Attentive Deep Neural Network for Exposing GAN-Generated Faces](http://arxiv.org/abs/2109.02167) | arXiv:2109.02167 [cs] | | 2021 | 429 | 430 | ### Segmentation 431 | 432 | | Title | Venue | Code | Year | 433 | | :--------------------------------------------------------------------------------------- | :-------------------: | :--: | :--: | 434 | | [Labels4Free: Unsupervised Segmentation Using StyleGAN](http://arxiv.org/abs/2103.14968) | arXiv:2103.14968 [cs] | | 2021 | 435 | | [BigDatasetGAN: Synthesizing ImageNet with Pixel-Wise Annotations](http://arxiv.org/abs/2201.04684) | ArXiv:2201.04684 [Cs] | | arXiv. 2022 | 436 | 437 | 438 | ### Datasets 439 | 440 | | Title | Venue | Code | Year | 441 | | :------------------------------------------------------------------------------------------------------------------------------- | :----: | :----------------------------------------------------------------------------------------------: | :---------: | 442 | | [Gradient-Based Learning Applied to Document Recognition]() | Proceedings of the IEEE | [mnist] | 1998 | 443 | | [Learning Multiple Layers of Features from Tiny Images]() | | [cifar] | 2009 | 444 | | [ImageNet: A Large-Scale Hierarchical Image Database](https://ieeexplore.ieee.org/document/5206848/) | CVPR | [ImageNet] | 2009 | 445 | | [Learning Hybrid Image Templates (HIT) by Information Projection]() | TPAMI | [AnimalFace](https://vcla.stat.ucla.edu/people/zhangzhang-si/HiT/exp5.html) | 2012 | 446 | | [A Style-Based Generator Architecture for Generative Adversarial Networks](http://arxiv.org/abs/1812.04948) | CVPR | [FFHQ]() | 2019 | 447 | | [StarGAN v2: Diverse Image Synthesis for Multiple Domains](http://arxiv.org/abs/1912.01865) | CVPR | [AFHQ](https://github.com/clovaai/stargan-v2/blob/master/README.md#animal-faces-hq-dataset-afhq) | 2020 | 448 | | [Automated Flower Classification over a Large Number of Classes]() | | [102Flowers](https://www.robots.ox.ac.uk/~vgg/data/flowers/102/index.html) | 2008 | 449 | | [XGAN: Unsupervised Image-to-Image Translation for Many-to-Many Mappings](http://arxiv.org/abs/1711.05139) | ICML | [CartoonSet](https://google.github.io/cartoonset/) | 2018 | 450 | | [Anime Faces Sourced from Safebooru Resized to 256x256](https://www.kaggle.com/scribbless/another-anime-face-dataset) | Kaggle | [AnimeFace](https://www.kaggle.com/scribbless/another-anime-face-dataset/metadata) | | 451 | | [Facial Expressions of Manga (Japanese Comic) Character Faces](https://www.kaggle.com/mertkkl/manga-facial-expressions) | Kaggle | [MangaExpressions](https://www.kaggle.com/mertkkl/manga-facial-expressions) | | 452 | | [Open-Source Cartoon Dataset](https://www.kaggle.com/arnaud58/photo2cartoon/version/1?select=trainB) | Kaggle | [photo2cartoon](https://www.kaggle.com/arnaud58/photo2cartoon/version/1?select=trainB) | 453 | | [Simpsons Faces: A Lot of Images of Your Favourite Characters](https://www.kaggle.com/kostastokis/simpsons-faces?select=cropped) | Kaggle | [SimpsonsFaces](https://www.kaggle.com/kostastokis/simpsons-faces?select=cropped) | | 454 | | [Bitmoji Faces](https://www.kaggle.com/mostafamozafari/bitmoji-faces) | Kaggle | [BitmojiFaces](https://www.kaggle.com/mostafamozafari/bitmoji-faces) | | 455 | | [BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation](https://arxiv.org/abs/2110.11728v1) | | [AAHQ](https://github.com/onion-liu/aahq-dataset) | 2021 | 456 | | :heart: [Fake It Till You Make It: Face Analysis in the Wild Using Synthetic Data Alone](http://arxiv.org/abs/2109.15102) | ICCV | [FaceSynthetics](https://github.com/microsoft/FaceSynthetics) | 2021 | 457 | | [Seeing 3D Chairs: Exemplar Part-Based 2D-3D Alignment Using a Large Dataset of CAD Models]() | CVPR | chair | 2014 | 458 | | [A Large-Scale Car Dataset for Fine-Grained Categorization and Verification](http://arxiv.org/abs/1506.08959) | CVPR | [CompCars] | arXiv. 2015 | 459 | | [The ArtBench Dataset: Benchmarking Generative Models with Artworks](https://github.com/liaopeiyuan/artbench) | 2022 | 460 | | [DwNet: Dense Warp-Based Network for Pose-Guided Human Video Generation](http://arxiv.org/abs/1910.09139) | BMVC | [Fashion](https://github.com/ubc-vision/DwNet) | 2019 | 461 | | [MoCoGAN: Decomposing Motion and Content for Video Generation](http://arxiv.org/abs/1707.04993) | CVPR | [Tai-Chi] | 2018 | 462 | | [Text2Human: Text-Driven Controllable Human Image Generation]() | ACM Transactions on Graphics (TOG) | [DeepFashion-MultiModal](https://github.com/yumingj/DeepFashion-MultiModal) | 2022 | 463 | 464 | 465 | 466 | ### alias (ref) 467 | 468 | | Title | Venue | Code | Year | 469 | | :---------------------------------------------------------------------------------------------------------- | :-------------------------: | :--: | :--: | 470 | | [Alias-Free Generative Adversarial Networks](http://arxiv.org/abs/2106.12423) | arXiv:2106.12423 [cs, stat] | | 2021 | 471 | | [On Buggy Resizing Libraries and Surprising Subtleties in FID Calculation](http://arxiv.org/abs/2104.11222) | arXiv:2104.11222 [cs] | | 2021 | 472 | 473 | 474 | ### Texture 475 | 476 | - https://github.com/carson-katri/dream-textures 477 | 478 | ### Tiles 479 | 480 | | Title | Venue | Code | Year | 481 | | :---------------------------------------------------------------------------------------------------------- | :-------------------------: | :--: | :--: | 482 | | [TileGAN: Synthesis of Large-Scale Non-Homogeneous Textures](http://arxiv.org/abs/1904.12795) | ACM Transactions on Graphics | | 2019 | 483 | | [InsetGAN for Full-Body Image Generation](http://arxiv.org/abs/2203.07293) | arXiv:2203.07293 [cs] | | 2022 | 484 | | [Collaging Class-Specific GANs for Semantic Image Synthesis](http://arxiv.org/abs/2110.04281) | ICCV | | 2021 | 485 | 486 | 487 | 488 | ## GAN application 489 | 490 | | Title | Venue | Code | Year | 491 | | :--------------------------------------------------------------------------------------------------------------------------------- | :-------------------: | :--: | :--: | 492 | | [SC-FEGAN: Face Editing Generative Adversarial Network with User’s Sketch and Color](http://arxiv.org/abs/1902.06838) | arXiv:1902.06838 [cs] | | 2019 | 493 | | [Semantic Text-to-Face GAN -ST^2FG](http://arxiv.org/abs/2107.10756) | arXiv:2107.10756 [cs] | | 2021 | 494 | | [CRD-CGAN: Category-Consistent and Relativistic Constraints for Diverse Text-to-Image Generation](http://arxiv.org/abs/2107.13516) | arXiv:2107.13516 [cs] | | 2021 | 495 | 496 | ## Image-to-Image Translation 497 | 498 | | Title | Venue | Code | Year | 499 | | :---------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------: | :----------------------------------------------------------------------------------------------: | :--: | 500 | | [Image-to-Image Translation with Conditional Adversarial Networks](http://arxiv.org/abs/1611.07004) | CVPR | [pix2pix]() | 2017 | 501 | | [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](http://arxiv.org/abs/1711.11585) | CVPR | [pix2pix-HD]() | 2018 | 502 | | [Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks](http://arxiv.org/abs/1703.10593) | ICCV | [CycleGAN]() | 2017 | 503 | | [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](http://arxiv.org/abs/1711.09020) | CVPR | | 2018 | 504 | | [StarGAN v2: Diverse Image Synthesis for Multiple Domains](http://arxiv.org/abs/1912.01865) | CVPR | | 2020 | 505 | | [Multimodal Unsupervised Image-to-Image Translation](http://arxiv.org/abs/1804.04732) | arXiv:1804.04732 [cs, stat] | [MUNIT]() | 2018 | 506 | | [High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network](http://arxiv.org/abs/2105.09188) | arXiv:2105.09188 [cs] | | 2021 | 507 | | [MixerGAN: An MLP-Based Architecture for Unpaired Image-to-Image Translation](http://arxiv.org/abs/2105.14110) | arXiv:2105.14110 [cs] | | 2021 | 508 | | [GANs N’ Roses: Stable, Controllable, Diverse Image to Image Translation (Works for Videos Too!)](http://arxiv.org/abs/2106.06561) | arXiv:2106.06561 [cs] | | 2021 | 509 | | :heart: [Sketch Your Own GAN](http://arxiv.org/abs/2108.02774) | ICCV | | 2021 | 510 | | [Contrastive Learning for Unpaired Image-to-Image Translation](http://arxiv.org/abs/2007.15651) | ECCV | [contrastive-unpaired-translation](https://github.com/taesungp/contrastive-unpaired-translation) | 2020 | 511 | | [The Animation Transformer: Visual Correspondence via Segment Matching](http://arxiv.org/abs/2109.02614) | arXiv:2109.02614 [cs] | | 2021 | 512 | | [Image Synthesis via Semantic Composition](http://arxiv.org/abs/2109.07053) | ICCV | | 2021 | 513 | | [You Only Need Adversarial Supervision for Semantic Image Synthesis](http://arxiv.org/abs/2012.04781) | arXiv:2012.04781 [cs, eess] | | 2020 | 514 | 515 | ## Style transfer 516 | 517 | - https://github.com/nrupatunga/L0-Smoothing 518 | 519 | | Title | Venue | Code | Year | 520 | | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------: | :-------------------------------------------------------------------------------------: | :--: | 521 | | [Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization](http://arxiv.org/abs/1703.06868) | ICCV | | 2017 | 522 | | [Texture Synthesis Using Convolutional Neural Networks](http://arxiv.org/abs/1505.07376) | NeurIPS | | 2015 | 523 | | [A Neural Algorithm of Artistic Style](http://arxiv.org/abs/1508.06576) | arXiv:1508.06576 [cs, q-bio] | | 2015 | 524 | | [Image Style Transfer Using Convolutional Neural Networks](https://www.cv-foundation.org/openaccess/content_cvpr_2016/html/Gatys_Image_Style_Transfer_CVPR_2016_paper.html) | CVPR | | 2016 | 525 | | [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](http://arxiv.org/abs/1603.08155) | ECCV | | 2016 | 526 | | [Texture Networks: Feed-Forward Synthesis of Textures and Stylized Images](http://arxiv.org/abs/1603.03417) | ICML | | 2016 | 527 | | [Attention-Based Stylisation for Exemplar Image Colourisation](http://arxiv.org/abs/2105.01705) | arXiv:2105.01705 [cs, eess] | | 2021 | 528 | | [StyleBank: An Explicit Representation for Neural Image Style Transfer](https://arxiv.org/abs/1703.09210v2) | | [Stylebank](https://github.com/jxcodetw/Stylebank) | 2017 | 529 | | [Rethinking and Improving the Robustness of Image Style Transfer](http://arxiv.org/abs/2104.05623) | arXiv:2104.05623 [cs, eess] | | 2021 | 530 | | [Paint Transformer: Feed Forward Neural Painting with Stroke Prediction](http://arxiv.org/abs/2108.03798) | ICCV | | 2021 | 531 | | :heart: [AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer](http://arxiv.org/abs/2108.03647) | ICCV | | 2021 | 532 | | [ZiGAN: Fine-Grained Chinese Calligraphy Font Generation via a Few-Shot Style Transfer Approach](http://arxiv.org/abs/2108.03596) | arXiv:2108.03596 [cs] | | 2021 | 533 | | [Domain-Aware Universal Style Transfer](http://arxiv.org/abs/2108.04441) | ICCV | | 2021 | 534 | | [Aesthetics and Neural Network Image Representations](http://arxiv.org/abs/2109.08103) | arXiv:2109.08103 [cs, eess, q-bio] | | 2021 | 535 | | :heart: [Collaborative Distillation for Ultra-Resolution Universal Style Transfer](http://arxiv.org/abs/2003.08436) | CVPR | [collaborative-distillation](https://github.com/mingsun-tse/collaborative-distillation) | 2020 | 536 | | [Adaptive Convolutions for Structure-Aware Style Transfer]() | CVPR | [ada-conv-pytorch](https://github.com/RElbers/ada-conv-pytorch) | 2021 | 537 | | [CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer](http://arxiv.org/abs/2207.04808) | ECCV | [CCPL](https://github.com/JarrentWu1031/CCPL) | arXiv. 2022 | 538 | 539 | 540 | ## Metric & perceptual loss 541 | 542 | | Title | Venue | Code | Year | 543 | | :------------------------------------------------------------------------------------------------------------------- | :-------------------: | :---------------------------------------------------------------------------------: | :--: | 544 | | [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](http://arxiv.org/abs/1801.03924) | arXiv:1801.03924 [cs] | [lpips-pytorch](https://github.com/S-aiueo32/lpips-pytorch) | 2018 | 545 | | [Generating Images with Perceptual Similarity Metrics Based on Deep Networks](http://arxiv.org/abs/1602.02644) | NeurIPS | Perceptual Similarity | 2016 | 546 | | [Generic Perceptual Loss for Modeling Structured Output Dependencies](http://arxiv.org/abs/2103.10571) | CVPR | [random] | 2021 | 547 | | [Inverting Adversarially Robust Networks for Image Synthesis](http://arxiv.org/abs/2106.06927) | arXiv:2106.06927 [cs] | | 2021 | 548 | | [Demystifying MMD GANs](http://arxiv.org/abs/1801.01401) | ICLR | Kernel Inception Distance (KID) | 2018 | 549 | | [GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium](http://arxiv.org/abs/1706.08500) | NeurIPS | Fréchet Inception Distance (FID) | 2017 | 550 | | [Improved Techniques for Training GANs](http://papers.nips.cc/paper/6125-improved-techniques-for-training-gans.pdf) | NeurIPS | Inception Score (IS) | 2016 | 551 | | [High-Fidelity Performance Metrics for Generative Models in PyTorch](https://github.com/toshas/torch-fidelity) | | torch-fidelity | 2020 | 552 | | [Reliable Fidelity and Diversity Metrics for Generative Models](http://arxiv.org/abs/2002.09797) | ICML | [generative-evaluation-prdc](https://github.com/clovaai/generative-evaluation-prdc) | 2020 | 553 | | [The Contextual Loss for Image Transformation with Non-Aligned Data](http://arxiv.org/abs/1803.02077) | ECCV | [contextualLoss](https://github.com/roimehrez/contextualLoss) | arXiv. 2018 | 554 | | [Maintaining Natural Image Statistics with the Contextual Loss](http://arxiv.org/abs/1803.04626) | ArXiv:1803.04626 [Cs] | | 2018 | 555 | 556 | 557 | ## Spectrum 558 | 559 | | Title | Venue | Code | Year | 560 | | :-------------------------------------------------------------------------------------------------------------------- | :-------------------: | :--: | :--: | 561 | | [Reproducibility of "FDA: Fourier Domain Adaptation ForSemantic Segmentation](http://arxiv.org/abs/2104.14749) | arXiv:2104.14749 [cs] | | 2021 | 562 | | [A Closer Look at Fourier Spectrum Discrepancies for CNN-Generated Images Detection](http://arxiv.org/abs/2103.17195) | CVPR | | 2021 | 563 | 564 | ## Weakly Supervised Object Localization 565 | 566 | | Title | Venue | Code | Year | 567 | | :------------------------------------------------------------------------------------------------------------------------ | :-------------------: | :--: | :--: | 568 | | [TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization](http://arxiv.org/abs/2103.14862) | arXiv:2103.14862 [cs] | | 2021 | 569 | | [Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Models](http://arxiv.org/abs/2105.08127) | arXiv:2105.08127 [cs] | | 2021 | 570 | | [Segmentation in Style: Unsupervised Semantic Image Segmentation with Stylegan and CLIP](http://arxiv.org/abs/2107.12518) | arXiv:2107.12518 [cs] | | 2021 | 571 | 572 | ## Implicit Neural Representations 573 | 574 | - [https://github.com/vsitzmann/awesome-implicit-representations](https://github.com/vsitzmann/awesome-implicit-representations) 575 | 576 | | Title | Venue | Code | Year | 577 | | :------------------------------------------------------------------------------------------------------------------ | :-------------------: | :--: | :--: | 578 | | [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](http://arxiv.org/abs/1901.05103) | arXiv:1901.05103 [cs] | | 2019 | 579 | | [Occupancy Networks: Learning 3D Reconstruction in Function Space](http://arxiv.org/abs/1812.03828) | arXiv:1812.03828 [cs] | | 2019 | 580 | | :heart: [Neural Image Representations for Multi-Image Fusion and Layer Separation](http://arxiv.org/abs/2108.01199) | arXiv:2108.01199 [cs] | | 2021 | 581 | | [Learning Continuous Image Representation with Local Implicit Image Function](http://arxiv.org/abs/2012.09161) | CVPR | | 2021 | 582 | 583 | 584 | ## Energy 585 | | Title | Venue | Code | Year | 586 | | :------------------------------------------------------------------------------------------------------------ | :-------------------------: | :-----------------------------------------------------------------------: | :--: | 587 | | [How to Train Your Energy-Based Models](http://arxiv.org/abs/2101.03288) | ArXiv:2101.03288 | | arXiv. 2021 | 588 | | [Your Classifier Is Secretly an Energy Based Model and You Should Treat It Like One](http://arxiv.org/abs/1912.03263) | ICLR | [JEM](https://github.com/wgrathwohl/JEM) | arXiv. 2020 | 589 | | [Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models](http://arxiv.org/abs/2209.06970) | NeurIPS | [Generative-Visual-Prompt](https://github.com/ChenWu98/Generative-Visual-Prompt) | 2022 | 590 | 591 | 592 | ## Flow 593 | 594 | | Title | Venue | Code | Year | 595 | | :------------------------------------------------------------------------------------------------------------ | :-------------------------: | :-----------------------------------------------------------------------: | :--: | 596 | | [Variational Inference with Normalizing Flows](http://arxiv.org/abs/1505.05770) | ICML | | 2015 | 597 | | [Density Estimation Using Real NVP](http://arxiv.org/abs/1605.08803) | ICLR | | arXiv. 2017 | 598 | 599 | 600 | ## ChatGPT 601 | 602 | - https://github.com/golfzert/chatgpt-chinese-prompt-hack 603 | - https://github.com/rawandahmad698/PyChatGPT 604 | 605 | ## Diffusion 606 | 607 | - https://github.com/heejkoo/Awesome-Diffusion-Models 608 | - https://github.com/huggingface/diffusers 609 | - https://github.com/Jack000/glid-3-xl 610 | - https://github.com/SirWaffle/AIrtist-k-diffusion-wrap 611 | - https://github.com/altryne/awesome-ai-art-image-synthesis 612 | - https://github.com/YangLing0818/Diffusion-Models-Papers-Survey-Taxonomy 613 | - https://github.com/Jack000/glid-3-xl-stable 614 | - https://github.com/Stability-AI/stablediffusion 615 | 616 | ### Generation 617 | | Title | Venue | Code | Year | 618 | | :------------------------------------------------------------------------------------------------------------ | :-------------------------: | :-----------------------------------------------------------------------: | :--: | 619 | | [Understanding Diffusion Models: A Unified Perspective](http://arxiv.org/abs/2208.11970) | arXiv:2208.11970 | | 2022 | 620 | | 1 [Deep Unsupervised Learning Using Nonequilibrium Thermodynamics](http://arxiv.org/abs/1503.03585) | ArXiv:1503.03585 [Cond-Mat, q-Bio, Stat] | | arXiv. 2015 | 621 | | 2 [Generative Modeling by Estimating Gradients of the Data Distribution](http://arxiv.org/abs/1907.05600) | NeurIPS | | 2019 | 622 | | 3 [Denoising Diffusion Probabilistic Models](http://arxiv.org/abs/2006.11239) | arXiv:2006.11239 [cs, stat] | [diffusion](https://github.com/hojonathanho/diffusion), [denoising-diffusion-pytorch](https://github.com/lucidrains/denoising-diffusion-pytorch) | 2020 | 623 | | [Denoising Diffusion Implicit Models](http://arxiv.org/abs/2010.02502) | ICLR | [DDIM] | arXiv. 2021 | 624 | | [Improved Denoising Diffusion Probabilistic Models](https://arxiv.org/abs/2102.09672v1) | ArXiv:2102.09672 [Cs.LG] | [improved-diffusion](https://github.com/openai/improved-diffusion) | 2021 | 625 | | [Score-Based Generative Modeling through Stochastic Differential Equations](https://openreview.net/forum?id=PxTIG12RRHS) | ICLR | | 2021 | 626 | | 35 steps [Elucidating the Design Space of Diffusion-Based Generative Models](http://arxiv.org/abs/2206.00364) | ArXiv:2206.00364 [Cs, Stat] | [k-diffusion](https://github.com/crowsonkb/k-diffusion) | arXiv. 2022 | 627 | | 10 steps [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](http://arxiv.org/abs/2206.00927) | ArXiv:2206.00927 [Cs, Stat] | [dpm-solver](https://github.com/LuChengTHU/dpm-solver) | arXiv. 2022 | 628 | | :heart: [SDEdit: Image Synthesis and Editing with Stochastic Differential Equations](http://arxiv.org/abs/2108.01073) | arXiv:2108.01073 [cs] | [SDEdit](https://github.com/ermongroup/SDEdit) | 2021 | 629 | | [D2C: Diffusion-Denoising Models for Few-Shot Conditional Generation](http://arxiv.org/abs/2106.06819) | arXiv:2106.06819 [cs] | | 2021 | 630 | | [Label-Efficient Semantic Segmentation with Diffusion Models](https://arxiv.org/abs/2112.03126v1) | | [ddpm-segmentation](https://github.com/yandex-research/ddpm-segmentation) | 2021 | 631 | | [Analog Bits: Generating Discrete Data Using Diffusion Models with Self-Conditioning](http://arxiv.org/abs/2208.04202) | | [bit-diffusion](https://github.com/lucidrains/bit-diffusion) | 2022 | 632 | | [Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise](http://arxiv.org/abs/2208.09392) | arXiv:2208.09392 | [Cold-Diffusion-Models](https://github.com/arpitbansal297/Cold-Diffusion-Models) | 2022 | 633 | | [Diffusion-GAN: Training GANs with Diffusion](http://arxiv.org/abs/2206.02262) | arXiv:2206.02262 | [Diffusion-GAN](https://github.com/Zhendong-Wang/Diffusion-GAN) | 2022 | 634 | | [Tackling the Generative Learning Trilemma with Denoising Diffusion GANs](http://arxiv.org/abs/2112.07804) | ICLR | [denoising-diffusion-gan](https://github.com/NVlabs/denoising-diffusion-gan) | 2022 | 635 | | [Score-Based Generative Modeling in Latent Space](http://arxiv.org/abs/2106.05931) | NeurIPS | [LSGM](https://github.com/NVlabs/LSGM) | arXiv. 2021 | 636 | | [Compositional Visual Generation with Composable Diffusion Models](http://arxiv.org/abs/2206.01714) | ECCV | [Composable-Diffusion](https://github.com/energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch) | arXiv. 2022 | 637 | | [Accelerating Score-Based Generative Models with Preconditioned Diffusion Sampling](http://arxiv.org/abs/2207.02196) | ECCV | [PDS](https://github.com/fudan-zvg/PDS) | 2022 | 638 | | [Diffusion Autoencoders: Toward a Meaningful and Decodable Representation](https://openaccess.thecvf.com/content/CVPR2022/html/Preechakul_Diffusion_Autoencoders_Toward_a_Meaningful_and_Decodable_Representation_CVPR_2022_paper.html) | CVPR | [diffae](https://github.com/phizaz/diffae) | 2022 | 639 | | [Cascaded Diffusion Models for High Fidelity Image Generation](http://arxiv.org/abs/2106.15282) | arXiv:2106.15282 | | 2021 | 640 | 641 | 642 | ### Inversion 643 | | Title | Venue | Code | Year | 644 | | :--------------------------------------------------------------------------------------------------------------------- | :--------------------------: | :--------------------------------------------------------: | :--: | 645 | | [ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models](http://arxiv.org/abs/2108.02938) | ICCV | [ilvr_adm](https://github.com/jychoi118/ilvr_adm) | arXiv. 2021 | 646 | | [Diffusion Models Beat GANs on Image Synthesis](http://arxiv.org/abs/2105.05233) | arXiv:2105.05233 [cs, stat] | [guided-diffusion](https://github.com/openai/guided-diffusion) | 2021 | 647 | | [An Image Is Worth One Word: Personalizing Text-to-Image Generation Using Textual Inversion](http://arxiv.org/abs/2208.01618) | arXiv:2208.01618 | [textual_inversion](https://github.com/rinongal/textual_inversion) | 2022 | 648 | | [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://arxiv.org/abs/2208.12242v1) | arXiv:2208.12242 | [dreambooth](https://dreambooth.github.io/),
[Dreambooth-Stable-Diffusion](https://github.com/XavierXiao/Dreambooth-Stable-Diffusion) | 2022 | 649 | | [DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation](http://arxiv.org/abs/2110.02711) | CVPR | [DiffusionCLIP](https://github.com/gwang-kim/DiffusionCLIP) | 2022 | 650 | 651 | ### Text-to-image 652 | - https://github.com/GeeveGeorge/Stable-Craiyon 653 | 654 | | Title | Venue | Code | Year | 655 | | :--------------------------------------------------------------------------------------------------------------------- | :--------------------------: | :--------------------------------------------------------: | :--: | 656 | | [Cross-Modal Contrastive Learning for Text-to-Image Generation](http://arxiv.org/abs/2101.04702) | CVPR | | 2021 | 657 | | [Zero-Shot Text-to-Image Generation](http://arxiv.org/abs/2102.12092) | ICML | | arXiv. 2021 | 658 | | [VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance](http://arxiv.org/abs/2204.08583) | ArXiv:2204.08583 | | 2022 | 659 | | [Learning Transferable Visual Models From Natural Language Supervision](https://arxiv.org/abs/2103.00020v1) | ICML | [CLIP](https://github.com/moein-shariatnia/OpenAI-CLIP)
[open_clip](https://github.com/mlfoundations/open_clip) | 2021 | 660 | | [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](http://arxiv.org/abs/2112.10741) | arXiv:2112.10741 | | 2022 | 661 | | [Hierarchical Text-Conditional Image Generation with CLIP Latents](http://arxiv.org/abs/2204.06125) | | [DALLE2-pytorch](https://github.com/lucidrains/DALLE2-pytorch) | 2022 | 662 | | [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://arxiv.org/abs/2205.11487v1) | | [imagen-pytorch](https://github.com/lucidrains/imagen-pytorch), [Imagen-pytorch](https://github.com/cene555/Imagen-pytorch) | 2022 | 663 | | [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation] | | [parti](https://github.com/google-research/parti) | | 664 | | [CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers](http://arxiv.org/abs/2204.14217) | arXiv:2204.14217 | | 2022 | 665 | | [High-Resolution Image Synthesis with Latent Diffusion Models](http://arxiv.org/abs/2112.10752) | CVPR | [stable-diffusion](https://github.com/pesser/stable-diffusion), [latent-diffusion](https://github.com/CompVis/latent-diffusion), [stable-diffusion](https://github.com/CompVis/stable-diffusion) | arXiv. 2022 | 666 | | [Prompt-to-Prompt Image Editing with Cross Attention Control](http://arxiv.org/abs/2208.01626) | arXiv:2208.01626 | [CrossAttentionControl](https://github.com/bloc97/CrossAttentionControl) | 2022 | 667 | | [SINE: SINgle Image Editing with Text-to-Image Diffusion Models](http://arxiv.org/abs/2212.04489) | arXiv:2212.04489 | [SINE](https://github.com/zhang-zx/SINE) | 2022 | 668 | 669 | 670 | ### Image_to_image 671 | 672 | | Title | Venue | Code | Year | 673 | | :--------------------------------------------------------------------------------------------------------------------- | :--------------------------: | :--------------------------------------------------------: | :--: | 674 | | [Palette: Image-to-Image Diffusion Models](http://arxiv.org/abs/2111.05826) | arXiv:2111.05826 | [Palette-Image-to-Image-Diffusion-Models](https://github.com/Janspiry/Palette-Image-to-Image-Diffusion-Models) | 2022 | 675 | | [Image Super-Resolution via Iterative Refinement](http://arxiv.org/abs/2104.07636) | arXiv:2104.07636 | [Image-Super-Resolution-via-Iterative-Refinement](https://github.com/Janspiry/Image-Super-Resolution-via-Iterative-Refinement) | 2021 | 676 | 677 | ### 3D 678 | 679 | - https://github.com/neverix/pixel-dreamfusion 680 | 681 | | Title | Venue | Code | Year | 682 | | :--------------------------------------------------------------------------------------------------------------------- | :--------------------------: | :--------------------------------------------------------: | :--: | 683 | | [RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation](http://arxiv.org/abs/2211.09869) | arXiv:2211.09869 | | 2022 | 684 | | [Magic3D: High-Resolution Text-to-3D Content Creation](http://arxiv.org/abs/2211.10440) | arXiv:2211.10440 | | 2022 | 685 | 686 | ### Detection 687 | 688 | | Title | Venue | Code | Year | 689 | | :--------------------------------------------------------------------------------------------------------------------- | :--------------------------: | :--------------------------------------------------------: | :--: | 690 | | [DiffusionInst: Diffusion Model for Instance Segmentation](http://arxiv.org/abs/2212.02773) | arXiv:2212.02773 | [DiffusionInst](https://github.com/chenhaoxing/DiffusionInst) | 2022 | 691 | 692 | 693 | 694 | ## 3D & NeRF 695 | 696 | - https://www.meshlab.net/ 697 | 698 | | Title | Venue | Code | Year | 699 | | :--------------------------------------------------------------------------------------------------------------------- | :--------------------------: | :--------------------------------------------------------: | :--: | 700 | | Efficient Ray Tracing of Volume Data | ACM Transactions on Graphics | | 1990 | 701 | | [Surface Light Fields for 3D Photography](https://doi.org/10.1145/344779.344925) | SIGGRAPH | | 2000 | 702 | | [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](http://arxiv.org/abs/2008.02268) | arXiv:2008.02268 [cs] | [nerfw](https://github.com/PeterouZh/nerf_pl/tree/nerfw) | 2021 | 703 | | [Modulated Periodic Activations for Generalizable Local Functional Representations](http://arxiv.org/abs/2104.03960) | arXiv:2104.03960 [cs] | | 2021 | 704 | | [Neural Volume Rendering: NeRF And Beyond](http://arxiv.org/abs/2101.05204) | arXiv:2101.05204 [cs] | [awesome-NeRF](https://github.com/yenchenlin/awesome-NeRF) | 2021 | 705 | | [Editing Conditional Radiance Fields](http://arxiv.org/abs/2105.06466) | arXiv:2105.06466 [cs] | [editnerf](https://github.com/stevliu/editnerf) | 2021 | 706 | | [Recursive-NeRF: An Efficient and Dynamically Growing NeRF](http://arxiv.org/abs/2105.09103) | arXiv:2105.09103 [cs] | | 2021 | 707 | | [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](http://arxiv.org/abs/2103.15595) | arXiv:2103.15595 [cs] | [mvsnerf](https://github.com/apchenstu/mvsnerf) | 2021 | 708 | | [Depth-Supervised NeRF: Fewer Views and Faster Training for Free](http://arxiv.org/abs/2107.02791) | arXiv:2107.02791 [cs] | | 2021 | 709 | | [Rethinking Positional Encoding](http://arxiv.org/abs/2107.02561) | arXiv:2107.02561 [cs] | | 2021 | 710 | | [Nerfies: Deformable Neural Radiance Fields](https://arxiv.org/abs/2011.12948v4) | arXiv:2011.12948 | [nerfies](https://github.com/google/nerfies) | 2020 | 711 | | [Self-Calibrating Neural Radiance Fields](http://arxiv.org/abs/2108.13826) | ICCV | | 2021 | 712 | | [Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering](http://arxiv.org/abs/2106.02634) | arXiv:2106.02634 [cs] | | 2021 | 713 | 714 | ### Sine 715 | 716 | | Title | Venue | Code | Year | Cite | 717 | | :-------------------------------------------------------------------------------------------------------------------------------------- | :-------------------: | :------------------------------------------------------: | :--: | :--: | 718 | | [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](http://arxiv.org/abs/2006.10739) | arXiv:2006.10739 [cs] | | 2020 | 719 | | :white_check_mark: [Implicit Neural Representations with Periodic Activation Functions](http://arxiv.org/abs/2006.09661) | NeurIPS | | 2020 | 720 | | :white_check_mark: [Modulated Periodic Activations for Generalizable Local Functional Representations](http://arxiv.org/abs/2104.03960) | arXiv:2104.03960 [cs] | | 2021 | 721 | | [Learned Initializations for Optimizing Coordinate-Based Neural Representations](http://arxiv.org/abs/2012.02189) | arXiv:2012.02189 [cs] | [nerf-meta](https://github.com/sanowar-raihan/nerf-meta) | 2021 | 722 | | [Seeing Implicit Neural Representations as Fourier Series](http://arxiv.org/abs/2109.00249) | arXiv:2109.00249 [cs] | | 2021 | 723 | 724 | ### INR 725 | 726 | | Title | Venue | Code | Year | Cite | 727 | | :-------------------------------------------------------------------------------------------------------- | :-------------------: | :----------------------------------------------: | :--: | :--: | 728 | | [Adversarial Generation of Continuous Images](http://arxiv.org/abs/2011.12026) | arXiv:2011.12026 [cs] | [inr-gan](https://github.com/universome/inr-gan) | 2020 | 729 | | [Image Generators with Conditionally-Independent Pixel Synthesis](http://arxiv.org/abs/2011.13775) | arXiv:2011.13775 [cs] | [CIPS](https://github.com/saic-mdal/CIPS) | 2020 | 730 | | [A Structured Dictionary Perspective on Implicit Neural Representations](http://arxiv.org/abs/2112.01917) | arXiv:2112.01917 [cs] | | 2021 | 731 | 732 | ### 3D & NeRF GANs 733 | 734 | - https://mrtornado24.github.io/Next3D/ 735 | 736 | | Title | Venue | Code | Year | Cite | 737 | | :------------------------------------------------------------------------------------------------------------------------------------------------ | :-------------------------: | :----------------------------------------------------: | :--: | :--: | 738 | | :heavy_check_mark: [HoloGAN: Unsupervised Learning of 3D Representations from Natural Images](http://arxiv.org/abs/1904.01326) | ICCV | | 2019 | 739 | | [BlockGAN: Learning 3D Object-Aware Scene Representations from Unlabelled Images](http://arxiv.org/abs/2002.08988) | NeurIPS | | 2020 | 740 | | :heavy_check_mark: [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](http://arxiv.org/abs/2007.02442) | arXiv:2007.02442 [cs] | | 2021 | 741 | | :heavy_check_mark: [Pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis](http://arxiv.org/abs/2012.00926) | arXiv:2012.00926 [cs] | [pi-GAN](https://github.com/marcoamonteiro/pi-GAN) | 2021 | 19 | 742 | | :heavy_check_mark: [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](http://arxiv.org/abs/2011.12100) | CVPR | [giraffe](https://github.com/autonomousvision/giraffe) | 2021 | 743 | | :heavy_check_mark: [GIRAFFE HD: A High-Resolution 3D-Aware Generative Model](http://arxiv.org/abs/2203.14954) | CVPR | | 2022 | 744 | | :heart: [StyleNeRF: A Style-Based 3D-Aware Generator for High-Resolution Image Synthesis](http://arxiv.org/abs/2110.08985) | arXiv:2110.08985 [cs, stat] | | 2021 | 745 | | [CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields](http://arxiv.org/abs/2103.17269) | arXiv:2103.17269 [cs] | | 2021 | 746 | | :heavy_check_mark: [GNeRF: GAN-Based Neural Radiance Field without Posed Camera](http://arxiv.org/abs/2103.15606) | arXiv:2103.15606 [cs] | [gnerf](https://github.com/MQ66/gnerf) | 2021 | 747 | | :heart: [Unconstrained Scene Generation with Locally Conditioned Radiance Fields](http://arxiv.org/abs/2104.00670) | ICCV | [ml-gsn](https://github.com/apple/ml-gsn) | 2021 | 748 | | [Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering](http://arxiv.org/abs/2109.01847) | ICCV | | 2021 | 749 | | :heavy_check_mark: [A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis](http://arxiv.org/abs/2110.15678) | NeurIPS | | 2021 | 750 | | :heavy_check_mark: [Generative Occupancy Fields for 3D Surface-Aware Image Synthesis](http://arxiv.org/abs/2111.00969) | NeurIPS | | 2021 | 751 | | :heavy_check_mark: [Efficient Geometry-Aware 3D Generative Adversarial Networks](http://arxiv.org/abs/2112.07945) | arXiv:2112.07945 [cs] | [eg3d](https://github.com/NVlabs/eg3d) | 2021 | 752 | | :heavy_check_mark: [3D-Aware Image Synthesis via Learning Structural and Textural Representations](http://arxiv.org/abs/2112.10759) | arXiv:2112.10759 [cs] | [VolumeGAN]() | 2021 | 753 | | :heavy_check_mark: [GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation](http://arxiv.org/abs/2112.08867) | arXiv:2112.08867 [cs] | [GRAM](https://github.com/microsoft/GRAM) | 2021 | 754 | | [CoordGAN: Self-Supervised Dense Correspondences Emerge from GANs](http://arxiv.org/abs/2203.16521) | CVPR | | 2022 | 755 | | :heavy_check_mark: [Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images](http://arxiv.org/abs/2203.15926) | CVPR | | 2022 | 756 | | :heavy_check_mark: [Multi-View Consistent Generative Adversarial Networks for 3D-Aware Image Synthesis](http://arxiv.org/abs/2204.06307) | CVPR | [MVCGAN](https://github.com/Xuanmeng-Zhang/MVCGAN) | 2022 | 757 | | :heavy_check_mark: [FENeRF: Face Editing in Neural Radiance Fields]() | CVPR | [FENeRF](https://github.com/MrTornado24/FENeRF) | 2022 | 758 | | :heavy_check_mark: [IDE-3D: Interactive Disentangled Editing for High-Resolution 3D-Aware Portrait Synthesis](http://arxiv.org/abs/2205.15517) | arXiv:2205.15517 | | 2022 | 759 | | :heavy_check_mark: [EpiGRAF: Rethinking Training of 3D GANs](http://arxiv.org/abs/2206.10535) | ArXiv:2206.10535 [Cs] | [epigraf](https://github.com/universome/epigraf) | arXiv. 2022 | 760 | | https://github.com/rethinking-3d-gans/code | | | | 761 | | :heart: [Generative Multiplane Images: Making a 2D GAN 3D-Aware](http://arxiv.org/abs/2207.10642) | ECCV | [ml-gmpi](https://github.com/apple/ml-gmpi) | arXiv. 2022 | 762 | | [GAUDI: A Neural Architect for Immersive 3D Scene Generation](http://arxiv.org/abs/2207.13751) | ArXiv:2207.13751 [Cs] | [ml-gaudi](https://github.com/apple/ml-gaudi) | arXiv. 2022 | 763 | | [Deep Deformable 3D Caricatures with Learned Shape Control](https://dl.acm.org/doi/10.1145/3528233.3530748) | SIGGRAPH |[DeepDeformable3DCaricatures](https://github.com/ycjungSubhuman/DeepDeformable3DCaricatures) | Vancouver BC Canada: ACM. 2022 | 764 | | [Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis](http://arxiv.org/abs/2207.10257) | ECCV | [SURF-GAN](https://github.com/jgkwak95/SURF-GAN) | arXiv. 2022 | 765 | | [Pix2NeRF: Unsupervised Conditional $\pi$-GAN for Single Image to Neural Radiance Fields Translation](http://arxiv.org/abs/2202.13162) | arXiv:2202.13162 [cs] | | 2022 | 766 | | [Training and Tuning Generative Neural Radiance Fields for Attribute-Conditional 3D-Aware Face Generation] | | [TT-GNeRF](https://github.com/zhangqianhui/TT-GNeRF) | | | 767 | 768 | ### Diffusion 769 | 770 | | Title | Venue | Code | Year | Cite | 771 | | :------------------------------------------------------------------------------------------------------------------------------------- | :----------------------: | :-----------------------------------------------------------------------------------------------------------: | :--: | :--: | 772 | | [DiffuStereo: High Quality Human Reconstruction via Diffusion-Based Stereo Using Sparse Cameras](http://arxiv.org/abs/2207.08000) | ECCV | [DiffuStereo](https://github.com/DSaurus/DiffuStereo) | arXiv. 2022 | 773 | | [DiffRF: Rendering-Guided 3D Radiance Field Diffusion](http://arxiv.org/abs/2212.01206) | arXiv:2212.01206 | [DiffRF](https://sirwyver.github.io/DiffRF/) | 2022 | 774 | 775 | 776 | ### NeRF large scene 777 | 778 | | Title | Venue | Code | Year | Cite | 779 | | :------------------------------------------------------------------------------------------------------------------------------------- | :----------------------: | :-----------------------------------------------------------------------------------------------------------: | :--: | :--: | 780 | | [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](http://arxiv.org/abs/2112.10703) | CVPR | | 2022 | 781 | | [Block-NeRF: Scalable Large Scene Neural View Synthesis](http://arxiv.org/abs/2202.05263) | CVPR | [BlockNeRFPytorch](https://github.com/dvlab-research/BlockNeRFPytorch) | arXiv. 2022 | 782 | | [IBRNet: Learning Multi-View Image-Based Rendering](http://arxiv.org/abs/2102.13090) | arXiv:2102.13090 [cs] | [IBRNet](https://github.com/googleinterns/IBRNet) | 2021 | 783 | 784 | ### NeRF 785 | 786 | - https://github.com/kakaobrain/NeRF-Factory/ :heart: 787 | - https://github.com/openxrlab/xrnerf 788 | - https://github.com/ActiveVisionLab/nerfmm 789 | - https://github.com/ventusff/improved-nerfmm 790 | - https://github.com/Kai-46/nerfplusplus 791 | - https://github.com/kwea123/nerf_pl 792 | - https://github.com/NVlabs/instant-ngp 793 | - https://github.com/sxyu/nerfvis 794 | - https://github.com/frozoul/4K-NeRF 795 | 796 | | Title | Venue | Code | Year | Cite | 797 | | :------------------------------------------------------------------------------------------------------------------------------------- | :----------------------: | :-----------------------------------------------------------------------------------------------------------: | :--: | :--: | 798 | | Ray Tracing Volume Densities | SIGGRAPH | | 1984 | 799 | | :white_check_mark: [NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis](http://arxiv.org/abs/2003.08934) | ECCV | [nerf-pytorch](https://github.com/yenchenlin/nerf-pytorch) | 2020 | 800 | | :white_check_mark: [NeRF--: Neural Radiance Fields Without Known Camera Parameters](http://arxiv.org/abs/2102.07064) | arXiv:2102.07064 [cs] | [nerfmm](https://github.com/PeterouZh/nerfmm), [improved-nerfmm](https://github.com/ventusff/improved-nerfmm) | 2021 | 801 | | :white_check_mark: [NeRF++: Analyzing and Improving Neural Radiance Fields](http://arxiv.org/abs/2010.07492) | arXiv:2010.07492 [cs] | [nerfplusplus](https://github.com/Kai-46/nerfplusplus) | 2020 | 802 | | :white_check_mark: [FastNeRF: High-Fidelity Neural Rendering at 200FPS](http://arxiv.org/abs/2103.10380) | arXiv:2103.10380 [cs] | | 2021 | 803 | | :white_check_mark: [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs](http://arxiv.org/abs/2103.13744) | ICCV | | 2021 | 804 | | [Plenoxels: Radiance Fields without Neural Networks](http://arxiv.org/abs/2112.05131) | arXiv:2112.05131 [cs] | [svox2](https://github.com/sxyu/svox2) | 2021 | 805 | | [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](http://arxiv.org/abs/2112.10703) | arXiv:2112.10703 [cs] | [mega-nerf](https://github.com/cmusatyalab/mega-nerf) | 2021 | 806 | | :heart: [Neural Sparse Voxel Fields](http://arxiv.org/abs/2007.11571) | arXiv:2007.11571 [cs] | [NSVF](https://github.com/facebookresearch/NSVF) | 2021 | 807 | | [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](http://arxiv.org/abs/2103.13415) | ICCV | | 2021 | 808 | | :heart: [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://arxiv.org/abs/2111.12077v2) | arXiv:2111.12077 [cs.CV] | | 2021 | 809 | | :heart: [Neural Actor: Neural Free-View Synthesis of Human Actors with Pose Control](http://arxiv.org/abs/2106.02019) | arXiv:2106.02019 [cs] | | 2022 | 810 | | [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding]() | | [instant-ngp](https://github.com/NVlabs/instant-ngp) | | | 811 | | :heart: [Point-NeRF: Point-Based Neural Radiance Fields](http://arxiv.org/abs/2201.08845) | arXiv:2201.08845 [cs] | [pointnerf](https://github.com/Xharlie/pointnerf) | 2022 | 812 | | [MoFaNeRF: Morphable Facial Neural Radiance Field](http://arxiv.org/abs/2112.02308) | arXiv:2112.02308 [cs] | | 2021 | 813 | | [Object-Centric Neural Scene Rendering](https://arxiv.org/abs/2012.08503v1) | 2020 | 814 | | [Semantic View Synthesis](https://arxiv.org/abs/2008.10598v1) | 2020 | 815 | | [NeRS: Neural Reflectance Surfaces for Sparse-View 3D Reconstruction in the Wild](https://arxiv.org/abs/2110.07604v3) | 2021 | 816 | | [MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis](http://arxiv.org/abs/2103.14910) | arXiv:2103.14910 [cs] | | 2021 | 817 | | :white_check_mark: [CodeNeRF: Disentangled Neural Radiance Fields for Object Categories](http://arxiv.org/abs/2109.01750) | ICCV | [code-nerf](https://github.com/wbjang/code-nerf) | 2021 | 818 | | [NeRF-SR: High-Quality Neural Radiance Fields Using Super-Sampling](http://arxiv.org/abs/2112.01759) | arXiv:2112.01759 [cs] | | 2021 | 819 | | :heart: [TensoRF: Tensorial Radiance Fields](http://arxiv.org/abs/2203.09517) | arXiv:2203.09517 [cs] | [TensoRF](https://github.com/apchenstu/TensoRF) | 2022 | 820 | | [Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fields](http://arxiv.org/abs/2203.10821) | arXiv:2203.10821 [cs] | | 2022 | 821 | | [CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields](http://arxiv.org/abs/2112.05139) | arXiv:2112.05139 [cs] | | 2022 | 822 | | [BARF: Bundle-Adjusting Neural Radiance Fields](http://arxiv.org/abs/2104.06405) | arXiv:2104.06405 [cs] | | 2021 | 823 | | [Unified Implicit Neural Stylization](http://arxiv.org/abs/2204.01943) | arXiv:2204.01943 [cs] | | 2022 | 824 | | [SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image](http://arxiv.org/abs/2204.00928) | arXiv:2204.00928 [cs] | | 2022 | 825 | | [NeRF-Editing: Geometry Editing of Neural Radiance Fields](http://arxiv.org/abs/2205.04978) | CVPR | [NeRF-Editing](https://github.com/IGLICT/NeRF-Editing) | 2022 | 826 | | [PixelNeRF: Neural Radiance Fields from One or Few Images](http://arxiv.org/abs/2012.02190) | CVPR | [pixel-nerf](https://github.com/sxyu/pixel-nerf) | 2021 | 827 | | [Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields](https://arxiv.org/abs/2112.03907v1) | CVPR | [refnerf](https://dorverbin.github.io/refnerf/) | 2022 | 828 | 829 | 830 | ### 3D inversion 831 | 832 | | Title | Venue | Code | Year | Cite | 833 | | :----------------------------------------------------------------------------------------------------------------------------------------- | :-------------------: | :-------------------------------------------------------------------------------: | :--: | :--: | 834 | | [Unsupervised 3D Shape Completion through GAN Inversion](http://arxiv.org/abs/2104.13366) | CVPR | | 2021 | 835 | | [3D GAN Inversion for Controllable Portrait Image Animation](http://arxiv.org/abs/2203.13441) | ArXiv:2203.13441 [Cs] | | arXiv. 2022 | 836 | | [Pix2NeRF: Unsupervised Conditional $\pi$-GAN for Single Image to Neural Radiance Fields Translation](http://arxiv.org/abs/2202.13162) | ArXiv:2202.13162 [Cs] | | arXiv. 2022 | 837 | | [Monocular 3D Object Reconstruction with GAN Inversion] | ECCV | | 2022 | 838 | | [INeRF: Inverting Neural Radiance Fields for Pose Estimation] IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) | | [inerf](https://github.com/salykovaa/inerf) | 2021 | 839 | | [Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion](http://arxiv.org/abs/2211.11674) | arXiv:2211.11674 | [nerf-from-image](https://github.com/google-research/nerf-from-image) | 2022 | 840 | 841 | 842 | 843 | 844 | ### Dynamic 845 | 846 | | Title | Venue | Code | Year | Cite | 847 | | :----------------------------------------------------------------------------------------------------------------------------------------- | :-------------------: | :-------------------------------------------------------------------------------: | :--: | :--: | 848 | | [Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes](http://arxiv.org/abs/2011.13084) | arXiv:2011.13084 [cs] | [Neural-Scene-Flow-Fields](https://github.com/zl548/Neural-Scene-Flow-Fields.git) | 2021 | 849 | | [D-NeRF: Neural Radiance Fields for Dynamic Scenes](http://arxiv.org/abs/2011.13961) | arXiv:2011.13961 [cs] | [D-NeRF](https://github.com/albertpumarola/D-NeRF) | 2020 | 850 | | [Dynamic View Synthesis from Dynamic Monocular Video](http://arxiv.org/abs/2105.06468) | arXiv:2105.06468 [cs] | [DynamicNeRF](https://github.com/gaochen315/DynamicNeRF) | 2021 | 851 | | :heart: [HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields](http://arxiv.org/abs/2106.13228) | arXiv:2106.13228 [cs] | [hypernerf](https://github.com/google/hypernerf) | 2021 | 852 | | [Neural Radiance Flow for 4D View Synthesis and Video Processing](https://arxiv.org/abs/2012.09790v2) | 2020 | 853 | | :heart: [Animatable Neural Implicit Surfaces for Creating Avatars from Videos](http://arxiv.org/abs/2203.08133) | arXiv:2203.08133 [cs] | | 2022 | 854 | 855 | ### Voice 856 | 857 | - https://github.com/CorentinJ/Real-Time-Voice-Cloning 858 | ### Hand 859 | 860 | - https://github.com/reyuwei/NIMBLE_model 861 | 862 | ### Hair 863 | 864 | - https://github.com/clach/Realtime-Vulkan-Hair 865 | 866 | ### Loose garment 867 | 868 | - https://cape.is.tue.mpg.de/dataset.html 869 | 870 | | Title | Venue | Code | Year | Cite | 871 | | :----------------------------------------------------------------------------------------------------------------------------------------- | :-------------------: | :-------------------------------------------------------------------------------: | :--: | :--: | 872 | | :heavy_check_mark: [Predicting Loose-Fitting Garment Deformations Using Bone-Driven Motion Networks](http://arxiv.org/abs/2205.01355) | SIGGRAPH | [VirtualBones](https://github.com/non-void/VirtualBones) | 2022 | 873 | | [TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style](http://arxiv.org/abs/2003.04583) | CVPR | [TailorNet_dataset](https://github.com/zycliao/TailorNet_dataset) | arXiv. 2020 | 874 | | [Learning Implicit Templates for Point-Based Clothed Human Modeling](https://arxiv.org/abs/2207.06955v1) | ECCV | | 2022 | 875 | | [3D Clothed Human Reconstruction in the Wild](https://arxiv.org/abs/2207.10053v1) | ECCV | [ClothWild_RELEASE](https://github.com/hygenie1228/ClothWild_RELEASE) | 2022 | 876 | | :heart: [TightCap: 3D Human Shape Capture with Clothing Tightness Field](http://arxiv.org/abs/1904.02601) | ACM Transactions on Graphics | [TightCap](https://github.com/ChenFengYe/TightCap) | 2021 | 877 | | [ARCH: Animatable Reconstruction of Clothed Humans](http://arxiv.org/abs/2004.04572) | CVPR | [ARCH](https://github.com/Tessantess/ARCH) | 2020 | 878 | 879 | 880 | ### Rigging 881 | 882 | | Title | Venue | Code | Year | Cite | 883 | | :----------------------------------------------------------------------------------------------------------------------------------------- | :-------------------: | :-------------------------------------------------------------------------------: | :--: | :--: | 884 | | :heart: [Learning Skeletal Articulations with Neural Blend Shapes] | ACM Transactions on Graphics | [neural-blend-shapes](https://github.com/PeizhuoLi/neural-blend-shapes) | 2021 | 885 | 886 | 887 | 888 | ### Anime Body 889 | | Title | Venue | Code | Year | 890 | | :----------------------------------------------------------------------------------------------------------------------- | :---------------------------------------: | :----------------------------------------------------------: | :--: | 891 | | [Collaborative Neural Rendering Using Anime Character Sheets](http://arxiv.org/abs/2207.05378) | ArXiv:2207.05378 [Cs] | [CoNR](https://github.com/megvii-research/CoNR) | arXiv. 2022 | 892 | 893 | 894 | ### Body 895 | 896 | - https://github.com/3DFaceBody/awesome-3dbody-papers 897 | - https://github.com/openMVG/awesome_3DReconstruction_list 898 | - https://github.com/ytrock/THuman2.0-Dataset 899 | - https://github.com/Danial-Kord/DigiHuman 900 | - https://github.com/zhaofuq/Instant-NSR 901 | 902 | 903 | | Title | Venue | Code | Year | 904 | | :----------------------------------------------------------------------------------------------------------------------- | :---------------------------------------: | :----------------------------------------------------------: | :--: | 905 | | [SMPL: A Skinned Multi-Person Linear Model]() | ACM Trans. Graphics (Proc. SIGGRAPH Asia) | | 2015 | 906 | | [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image]() | CVPR | [SMPL-X] | 2019 | 907 | | [AMASS: Archive of Motion Capture as Surface Shapes]() | ICCV | [AMASS](https://amass.is.tue.mpg.de/index.html) | 2019 | 908 | | :heavy_check_mark: [SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes](http://arxiv.org/abs/2104.03953) | ICCV | | 2021 | 909 | | :heavy_check_mark: [Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies](http://arxiv.org/abs/2105.02872) | ICCV | [animatable_nerf](https://github.com/zju3dv/animatable_nerf) | 2021 | 910 | | [Neural Actor: Neural Free-View Synthesis of Human Actors with Pose Control](http://arxiv.org/abs/2106.02019) | SIGGRAPH Asia | | 2021 | 911 | | :heavy_check_mark: [Animatable Neural Radiance Fields from Monocular RGB Videos](http://arxiv.org/abs/2106.13629) | ArXiv:2106.13629 [Cs] | [Anim-NeRF](https://github.com/JanaldoChen/Anim-NeRF) | arXiv. 2021 | 912 | | [VIBE: Video Inference for Human Body Pose and Shape Estimation](http://arxiv.org/abs/1912.05656) | CVPR | [VIBE](https://github.com/mkocabas/VIBE) | arXiv. 2020 | 913 | | :heavy_check_mark: [A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose](http://arxiv.org/abs/2102.06199) | NeurIPS | [A-NeRF](https://github.com/LemonATsu/A-NeRF) | arXiv. 2021 | 914 | | [HumanNeRF: Free-Viewpoint Rendering of Moving People from Monocular Video](http://arxiv.org/abs/2201.04127) | CVPR | [humannerf](https://github.com/chungyiweng/humannerf) | 2022 | 915 | | :heart: [The Power of Points for Modeling Humans in Clothing]() | ICCV | [POP](https://github.com/qianlim/POP) | 2021 | 916 | | :heart: [Neural Point-Based Shape Modeling of Humans in Challenging Clothing]() | International Conference on 3D Vision (3DV) | [SkiRT](https://github.com/qianlim/SkiRT) | 2022 | 917 | | [StylePeople: A Generative Model of Fullbody Human Avatars](http://arxiv.org/abs/2104.08363) | arXiv:2104.08363 [cs] | | 2021 | 918 | | [NPMs: Neural Parametric Models for 3D Deformable Shapes](http://arxiv.org/abs/2104.00702) | arXiv:2104.00702 [cs] | | 2021 | 919 | | :heart: [ICON: Implicit Clothed Humans Obtained from Normals](http://arxiv.org/abs/2112.09127) | arXiv:2112.09127 [cs] | [ICON](https://github.com/YuliangXiu/ICON) | 2022 | 920 | | :heart: [GDNA: Towards Generative Detailed Neural Avatars]() | CVPR | | 2022 | 921 | | [SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks]() | CVPR | | 2021 | 922 | | [NeuralAnnot: Neural Annotator for 3D Human Mesh Training Sets](http://arxiv.org/abs/2011.11232) | arXiv:2011.11232 [cs] | | 2022 | 923 | | :heart: [PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop](http://arxiv.org/abs/2103.16507) | ICCV | | 2021 | 924 | | :heart: [Structured Local Radiance Fields for Human Avatar Modeling](http://arxiv.org/abs/2203.14478) | CVPR | | arXiv. 2022 | 925 | | :heavy_check_mark: [SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video](http://arxiv.org/abs/2201.12792) | CVPR | [SelfRecon](https://jby1993.github.io/SelfRecon/) | arXiv. 2022 | 926 | | [ARAH: Animatable Volume Rendering of Articulated Human SDFs] | ECCV | [arah](https://github.com/taconite/arah-release) | 2022 | 927 | | [Neural Actor: Neural Free-View Synthesis of Human Actors with Pose Control](http://arxiv.org/abs/2106.02019) | SIGGRAPH Asia | [Neural_Actor_Main_Code](https://github.com/lingjie0206/Neural_Actor_Main_Code) | arXiv. 2021 | 928 | | :heart: [Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View Synthesis](http://arxiv.org/abs/2204.11798) | arXiv:2204.11798 [cs] | [gnr](https://github.com/generalizable-neural-performer/gnr) | 2022 | 929 | | :heart: [NeuMan: Neural Human Radiance Field from a Single Video](https://arxiv.org/abs/2203.12575v1) | ECCV | [ml-neuman](https://github.com/apple/ml-neuman) | 2022 | 930 | | [Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesis](http://arxiv.org/abs/2201.01683) | CVPR | [surface-aligned-nerf](https://github.com/pfnet-research/surface-aligned-nerf) | arXiv. 2022 | 931 | | [LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modeling](http://arxiv.org/abs/2208.08622) | ECCV | [LoRD](https://github.com/BoyanJIANG/LoRD) | 2022 | 932 | | [TAVA: Template-Free Animatable Volumetric Actors](http://arxiv.org/abs/2206.08929) | ECCV | [tava](https://github.com/facebookresearch/tava) | 2022 | 933 | | [Fast-SNARF: A Fast Deformer for Articulated Neural Fields]() | | [fast-snarf](https://github.com/xuchen-ethz/fast-snarf) | 2022 | 934 | | [InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds](http://arxiv.org/abs/2212.10550) | arXiv:2212.10550 | [InstantAvatar](https://tijiang13.github.io/InstantAvatar/) | 2022 | 935 | 936 | 937 | ### Body Generation 938 | 939 | - https://github.com/justimyhxu/awesome-3D-generation 940 | 941 | | Title | Venue | Code | Year | 942 | | :------------------------------------------------------------------------------------------------------------------ | :-------------------: | :--------------------------------------------------: | :--: | 943 | | [DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations]() | CVPR | [DeepFashion](https://mmlab.ie.cuhk.edu.hk/projects/DeepFashion.html) | 2016 | 944 | | [Text2Human: Text-Driven Controllable Human Image Generation]() | ACM Transactions on Graphics (TOG) | [Text2Human](https://github.com/yumingj/Text2Human) | 2022 | 945 | | [StyleGAN-Human: A Data-Centric Odyssey of Human Generation](http://arxiv.org/abs/2204.11823) | arXiv:2204.11823 [cs] | | 2022 | 946 | | :heavy_check_mark: [3D-Aware Semantic-Guided Generative Model for Human Synthesis](http://arxiv.org/abs/2112.01422) | arXiv:2112.01422 [cs] | | 2021 | 947 | | :heart: [InsetGAN for Full-Body Image Generation](http://arxiv.org/abs/2203.07293) | arXiv:2203.07293 [cs] | | 2022 | 948 | | [Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis](http://arxiv.org/abs/1909.12224) | ICCV | [impersonator](https://github.com/svip-lab/impersonator) | 2019 | 949 | | :heavy_check_mark: [SMPLpix: Neural Avatars from 3D Human Models](http://arxiv.org/abs/2008.06872) | Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision | [smplpix](https://github.com/sergeyprokudin/smplpix) | arXiv. 2021 | 950 | | [Neural Articulated Radiance Field](https://arxiv.org/abs/2104.03110v2) | ICCV | | 2021 | 951 | | [Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations](http://arxiv.org/abs/2204.08839) | ECCV | [ENARF-GAN](https://github.com/nogu-atsu/ENARF-GAN) | 2022 | 952 | | [Generative Neural Articulated Radiance Fields](http://arxiv.org/abs/2206.14314) | ArXiv:2206.14314 [Cs] | [gnarf](http://www.computationalimaging.org/publications/gnarf/) | arXiv. 2022 | 953 | | [AvatarGen: A 3D Generative Model for Animatable Human Avatars](http://arxiv.org/abs/2208.00561) | ArXiv:2208.00561 [Cs] | [AvatarGen](https://github.com/jfzhang95/AvatarGen) | arXiv. 2022 | 954 | | [EVA3D: Compositional 3D Human Generation from 2D Image Collections](http://arxiv.org/abs/2210.04888) | arXiv:2210.04888 | | 2022 | 955 | 956 | 957 | ### Body from video 958 | 959 | | Title | Venue | Code | Year | 960 | | :-------------------------------------------------------------------------------------------------------------------------------- | :-------------------: | :--: | :--: | 961 | | [SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video](http://arxiv.org/abs/2201.12792) | arXiv:2201.12792 [cs] | | 2022 | 962 | 963 | 964 | ### 3DMM Face 965 | 966 | - https://github.com/tencent-ailab/hifi3dface 967 | - https://github.com/ascust/3DMM-Fitting-Pytorch 968 | 969 | | Title | Venue | Code | Year | 970 | | :------------------------------------------------------------------------------------------------------------------------ | :-------------------: | :--------------------------------------------------------------------------: | :--: | 971 | | [Neural Head Reenactment with Latent Pose Descriptors](http://arxiv.org/abs/2004.12000) | CVPR | [latent-pose-reenactment](https://github.com/shrubb/latent-pose-reenactment) | 2020 | 972 | | [Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry](http://arxiv.org/abs/2110.09772) | arXiv:2110.09772 [cs] | | 2021 | 973 | | [REALY: Rethinking the Evaluation of 3D Face Reconstruction](http://arxiv.org/abs/2203.09729) | ECCV | [REALY](https://github.com/czh-98/REALY) | 2022 | 974 | 975 | ### 3D FACE Avatars 976 | 977 | - https://github.com/TimoBolkart/BFM_to_FLAME 978 | - https://github.com/HavenFeng/photometric_optimization 979 | - https://github.com/soubhiksanyal/FLAME_PyTorch 980 | - https://github.com/Azmarie/Face-Morphing 981 | 982 | | Title | Venue | Code | Year | 983 | | :---------------------------------------------------------------------------------------------------------------------------------------- | :--------------------------: | :--------------------------------------------------------------------: | :--: | 984 | | [A Morphable Model for the Synthesis of 3D Faces](https://doi.org/10.1145/311535.311556) | Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques | | SIGGRAPH ’99, USA: ACM Press/Addison-Wesley Publishing Co. 1999 | 985 | | [Learning a Model of Facial Shape and Expression from 4D Scans]() | ACM Transactions on Graphics | [FLAME] | 2017 | 986 | | :heart: [FLAME-in-NeRF : Neural Control of Radiance Fields for Free View Face Animation](http://arxiv.org/abs/2108.04913) | arXiv:2108.04913 [cs] | | 2021 | 987 | | [Learning a Model of Facial Shape and Expression from 4D Scans]() | ACM Transactions on Graphics | | 2017 | 988 | | :heart: [EMOCA: Emotion Driven Monocular Face Capture and Animation]() | CVPR | [emoca](https://github.com/radekd91/emoca) | 2022 | 989 | | [FaceVerse: A Fine-Grained and Detail-Controllable 3D Face Morphable Model from a Hybrid Dataset]() | CVPR | | 2022 | 990 | | [I M Avatar: Implicit Morphable Head Avatars from Videos](http://arxiv.org/abs/2112.07471) | CVPR | [IMavatar](https://github.com/zhengyuf/IMavatar) | 2022 | 991 | | :heavy_check_mark: [Neural Head Avatars from Monocular RGB Videos](http://arxiv.org/abs/2112.01554) | arXiv:2112.01554 [cs] | [neural-head-avatars](https://github.com/philgras/neural-head-avatars) | 2022 | 992 | | [PVA: Pixel-Aligned Volumetric Avatars](http://arxiv.org/abs/2101.02697) | arXiv:2101.02697 [cs] | | 2021 | 993 | | [AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis](http://arxiv.org/abs/2103.11078) | arXiv:2103.11078 [cs] | | 2021 | 994 | | [Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation](http://arxiv.org/abs/2201.07786) | arXiv:2201.07786 [cs, eess] | | 2022 | 995 | | [HeadGAN: One-Shot Neural Head Synthesis and Editing](http://arxiv.org/abs/2012.08261) | arXiv:2012.08261 [cs] | | 2021 | 996 | | [KeypointNeRF: Generalizing Image-Based Volumetric Avatars Using Relative Spatial Encoding of Keypoints](http://arxiv.org/abs/2205.04992) | arXiv:2205.04992 [cs] | | 2022 | 997 | | [Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set](http://arxiv.org/abs/1903.08527) | ArXiv:1903.08527 [Cs] | [Deep3DFaceRecon_pytorch](https://github.com/sicxu/Deep3DFaceRecon_pytorch) | arXiv. 2020 | 998 | 999 | 1000 | ### Stylization 1001 | 1002 | | Title | Venue | Code | Year | 1003 | | :--------------------------------------------------------------------------------------------------------- | :-------------------: | :-------------------------------------------------------------: | ---- | 1004 | | [Unified Implicit Neural Stylization](http://arxiv.org/abs/2204.01943) | ECCV | | arXiv. 2022 | 1005 | | [ARF: Artistic Radiance Fields](http://arxiv.org/abs/2206.06360) | ECCV | [ARF-svox2](https://github.com/Kai-46/ARF-svox2) | arXiv. 2022 | 1006 | | [UPST-NeRF: Universal Photorealistic Style Transfer of Neural Radiance Fields for 3D Scene](http://arxiv.org/abs/2208.07059) | arXiv:2208.07059 | [UPST-NeRF](https://github.com/semchan/UPST-NeRF) | 2022 | 1007 | 1008 | 1009 | ### Face Style 1010 | 1011 | | Title | Venue | Code | Year | 1012 | | :--------------------------------------------------------------------------------------------------------- | :-------------------: | :-------------------------------------------------------------: | ---- | 1013 | | [Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer](http://arxiv.org/abs/2203.13248) | arXiv:2203.13248 [cs] | [DualStyleGAN](https://github.com/williamyang1991/DualStyleGAN) | 2022 | 1014 | | [Stitch It in Time: GAN-Based Facial Editing of Real Videos](http://arxiv.org/abs/2201.08361) | arXiv. | [STIT](https://github.com/rotemtzaban/STIT) | 2022 | 1015 | | [Fix the Noise: Disentangling Source Feature for Transfer Learning of StyleGAN](http://arxiv.org/abs/2204.14079) | ArXiv:2204.14079 [Cs] | [FixNoise](https://github.com/LeeDongYeun/FixNoise) | arXiv. 2022 | 1016 | | [AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment](http://arxiv.org/abs/2111.07640) | ECCV | [AnimeCeleb](https://github.com/kangyeolk/AnimeCeleb) | arXiv. 2022 | 1017 | | [DCT-Net: Domain-Calibrated Translation for Portrait Stylization](http://arxiv.org/abs/2207.02426) | ACM Transactions on Graphics | [DCT-Net](https://github.com/menyifang/DCT-Net) | 2022 | 1018 | | [VToonify: Controllable High-Resolution Portrait Video Style Transfer]() | ACM Transactions on Graphics (TOG) | [VToonify](https://github.com/williamyang1991/VToonify) | n.d. | 1019 | | [BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation](https://arxiv.org/abs/2110.11728v1) | NeurIPS | [BlendGAN](https://github.com/onion-liu/BlendGAN) | 2021 | 1020 | | [Unpaired Cartoon Image Synthesis via Gated Cycle Mapping]() | CVPR | | 2022 | 1021 | 1022 | 1023 | ### Face Animation 1024 | 1025 | | Title | Venue | Code | Year | 1026 | | :------------------------------------------------------------------------------------ | :---: | :--: | ---- | 1027 | | [Thin-Plate Spline Motion Model for Image Animation](http://arxiv.org/abs/2203.14367) | CVPR | | 2022 | 1028 | | [Depth-Aware Generative Adversarial Network for Talking Head Video Generation](http://arxiv.org/abs/2203.06605) | CVPR | [DaGAN](https://github.com/harlanhong/CVPR2022-DaGAN) | arXiv. 2022 | 1029 | 1030 | 1031 | ### Renderer & Regularization 1032 | - https://github.com/ventusff/neurecon 1033 | 1034 | 1035 | | Title | Venue | Code | Year | 1036 | | :--------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------: | :-------------------------------------------------------------: | ---- | 1037 | | [Implicit Geometric Regularization for Learning Shapes](http://arxiv.org/abs/2002.10099) | ICML | [Eikonal] | 2020 | 1038 | | [Neural 3D Scene Reconstruction with the Manhattan-World Assumption](http://arxiv.org/abs/2205.02836) | CVPR | [manhattan_sdf](https://github.com/zju3dv/manhattan_sdf) | 2022 | 1039 | | :heart: [Differentiable Signed Distance Function Rendering]() | Transactions on Graphics (Proceedings of SIGGRAPH) | [sdf](https://github.com/lucidrains/differentiable-SDF-pytorch) | 2022 | 1040 | | [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-View Reconstruction](http://arxiv.org/abs/2106.10689) | | [NeuS](https://github.com/Totoro97/NeuS) | 2021 | 1041 | | [SNeS: Learning Probably Symmetric Neural Surfaces from Incomplete Data](https://arxiv.org/abs/2206.06340v1) | ECCV | [snes](https://github.com/eldar/snes) | 2022 | 1042 | | :heart: [Volume Rendering of Neural Implicit Surfaces](http://arxiv.org/abs/2106.12052) | arXiv:2106.12052 [cs] | [volsdf](https://github.com/lioryariv/volsdf) | 2021 | 1043 | | [Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance](https://arxiv.org/abs/2003.09852v3) | NeurIPS | [idr](https://github.com/lioryariv/idr) | 2020 | 1044 | | :heavy_check_mark: [Multi-View Mesh Reconstruction With Neural Deferred Shading](https://openaccess.thecvf.com/content/CVPR2022/html/Worchel_Multi-View_Mesh_Reconstruction_With_Neural_Deferred_Shading_CVPR_2022_paper.html) | CVPR | [neural-deferred-shading](https://github.com/fraunhoferhhi/neural-deferred-shading) | 2022 | 1045 | | :heart: [IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Images](http://arxiv.org/abs/2204.02232) | CVPR | [IRON](https://github.com/Kai-46/IRON) | arXiv. 2022 | 1046 | | :heavy_check_mark: [UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction]() | ICCV | [unisurf](https://github.com/autonomousvision/unisurf) | 2021 | 1047 | | [MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction](https://arxiv.org/abs/2206.00665v1) | ArXiv:2206.00665 | | 2022 | 1048 | | [Direct Voxel Grid Optimization: Super-Fast Convergence for Radiance Fields Reconstruction](http://arxiv.org/abs/2111.11215) | CVPR | [DirectVoxGO](https://github.com/sunset1995/DirectVoxGO) | arXiv. 2022 | 1049 | | [Improved Direct Voxel Grid Optimization for Radiance Fields Reconstruction](http://arxiv.org/abs/2206.05085) | ArXiv:2206.05085 [Cs] | | arXiv. 2022 | 1050 | | [Improved Surface Reconstruction Using High-Frequency Details](http://arxiv.org/abs/2206.07850) | ArXiv:2206.07850 [Cs] | | arXiv. 2022 | 1051 | | [InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering](http://arxiv.org/abs/2112.15399) | CVPR | [InfoNeRF](https://github.com/mjmjeong/InfoNeRF) | arXiv. 2022 | 1052 | | [Improving Neural Implicit Surfaces Geometry with Patch Warping](http://arxiv.org/abs/2112.09648) | CVPR | [NeuralWarp](https://github.com/fdarmon/NeuralWarp) | arXiv. 2022 | 1053 | | [SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Views](http://arxiv.org/abs/2206.05737) | ECCV | [SparseNeuS](https://github.com/xxlong0/SparseNeuS) | arXiv. 2022 | 1054 | | [NeuMesh: Learning Disentangled Neural Mesh-Based Implicit Field for Geometry and Texture Editing] | ECCV | [NeuMesh](https://github.com/zju3dv/NeuMesh) | 2022 | 1055 | | [Neural Density-Distance Fields](http://arxiv.org/abs/2207.14455) | ECCV | [neddf](https://github.com/ueda0319/neddf) | arXiv. 2022 | 1056 | | [Neural 3D Reconstruction in the Wild](http://arxiv.org/abs/2205.12955) | SIGGRAPH | [NeuralRecon-W](https://github.com/zju3dv/NeuralRecon-W) | 2022 | 1057 | | :heart: [KeypointNeRF: Generalizing Image-Based Volumetric Avatars Using Relative Spatial Encoding of Keypoints](http://arxiv.org/abs/2205.04992) | arXiv:2205.04992 [cs] | [KeypointNeRF](https://github.com/facebookresearch/KeypointNeRF) | 2022 | 1058 | | [GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction](http://arxiv.org/abs/2206.14735) | International Conference on 3D Vision (3DV) | [go-surf](https://github.com/JingwenWang95/go-surf) | 2022 | 1059 | 1060 | 1061 | ### Material and lighting 1062 | 1063 | | Title | Venue | Code | Year | 1064 | | :--------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------: | :-------------------------------------------------------------: | ---- | 1065 | | [NeILF: Neural Incident Light Field for Physically-Based Material Estimation](http://arxiv.org/abs/2203.07182) | ECCV | [neilf](https://github.com/apple/ml-neilf) | arXiv. 2022 | 1066 | | [NeRF for Outdoor Scene Relighting] | ECCV | [NeRF-OSR](https://github.com/r00tman/NeRF-OSR) | 2022 | 1067 | 1068 | 1069 | ### Motion 1070 | 1071 | - https://github.com/xianfei/SysMocap 1072 | - https://github.com/zju3dv/EasyMocap 1073 | - https://github.com/EricGuo5513/HumanML3D 1074 | 1075 | | Title | Venue | Code | Year | 1076 | | :--------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------: | :-------------------------------------------------------------: | ---- | 1077 | | [GANimator: Neural Motion Synthesis from a Single Sequence]() | ACM Transactions on Graphics (TOG) | [ganimator](https://github.com/PeizhuoLi/ganimator) | 2022 | 1078 | | [Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects] | CVPR | [watch-it-move](https://github.com/NVlabs/watch-it-move) | 2022 | 1079 | | [Learn to Dance with AIST++: Music Conditioned 3D Dance Generation]() | ICCV | | 2021 | 1080 | | [Talking Head(?) Anime from a Single Image 3: Now the Body Too](http://pkhungurn.github.io/talking-head-anime-3/) | | [talking-head-anime](https://github.com/pkhungurn/talking-head-anime-3-demo) | 2022 | 1081 | | [PhysCap: Physically Plausible Monocular 3D Motion Capture in Real Time]() | ACM Transactions on Graphics | | 2020 | 1082 | | [The Wanderings of Odysseus in 3D Scenes](http://arxiv.org/abs/2112.09251) | CVPR | [GAMMA](https://github.com/yz-cnsdqz/GAMMA-release) | arXiv. 2022 | 1083 | | [Adversarial Parametric Pose Prior](http://arxiv.org/abs/2112.04203) | CVPR | [adv_param_pose_prior](https://github.com/cvlab-epfl/adv_param_pose_prior) | arXiv. 2022 | 1084 | | [AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars](http://arxiv.org/abs/2205.08535) | SIGGRAPH | [AvatarCLIP](https://github.com/hongfz16/AvatarCLIP) | 2022 | 1085 | | [SOMA: Solving Optical Marker-Based MoCap Automatically] | ICCV | [soma](https://github.com/nghorbani/soma) | 2021 | 1086 | | [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](http://arxiv.org/abs/2208.15001) | arXiv:2208.15001 | [MotionDiffuse](https://github.com/mingyuan-zhang/MotionDiffuse) | 2022 | 1087 | | [TEACH: Temporal Action Composition for 3D Humans](http://arxiv.org/abs/2209.04066) | International Conference on 3D Vision (3DV) | [teach](https://github.com/athn-nik/teach) | arXiv. 2022 | 1088 | | [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](http://arxiv.org/abs/2207.01696) | ECCV | [TM2T](https://github.com/EricGuo5513/TM2T) | 2022 | 1089 | 1090 | 1091 | ### Shape generation 1092 | 1093 | | Title | Venue | Code | Year | 1094 | | :--------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------: | :-------------------------------------------------------------: | ---- | 1095 | | [Learning Implicit Fields for Generative Shape Modeling](http://arxiv.org/abs/1812.02822) | arXiv:1812.02822 [cs] | | 2019 | 1096 | 1097 | 1098 | ### SMPL estimation 1099 | - https://github.com/open-mmlab/mmhuman3d 1100 | 1101 | 1102 | | Title | Venue | Code | Year | 1103 | | :--------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------: | :-------------------------------------------------------------: | ---- | 1104 | | [End-to-End Recovery of Human Shape and Pose](http://arxiv.org/abs/1712.06584) | CVPR | [hmr] | arXiv. 2018 | 1105 | | [VIBE: Video Inference for Human Body Pose and Shape Estimation](http://arxiv.org/abs/1912.05656) | CVPR | [VIBE](https://github.com/mkocabas/VIBE) | arXiv. 2020 | 1106 | | [TransPose: Real-Time 3D Human Translation and Pose Estimation with Six Inertial Sensors]() | ACM Transactions on Graphics | [TransPose](https://github.com/Xinyu-Yi/TransPose) | 2021 | 1107 | | [Monocular Expressive Body Regression through Body-Driven Attention](https://expose.is.tue.mpg.de) | European Conference on Computer Vision (ECCV) | [expose](https://github.com/vchoutas/expose) | 2020 | 1108 | | [Human Mesh Recovery from Multiple Shots](http://arxiv.org/abs/2012.09843) | CVPR | [multishot](https://github.com/geopavlakos/multishot) | arXiv. 2022 | 1109 | | :heart: [Learned Vertex Descent: A New Direction for 3D Human Model Fitting](http://arxiv.org/abs/2205.06254) | ECCV | [LVD](https://github.com/enriccorona/LVD) | arXiv. 2022 | 1110 | | [DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation](http://arxiv.org/abs/2203.08713) | ECCV | [DeciWatch](https://github.com/cure-lab/DeciWatch) | arXiv. 2022 | 1111 | | [PARE: Part Attention Regressor for 3D Human Body Estimation](http://arxiv.org/abs/2104.08527) | ICCV | [PARE](https://github.com/mkocabas/PARE) | arXiv. 2021 | 1112 | | [Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers](http://arxiv.org/abs/2207.13820) | ECCV | [FastMETRO](https://github.com/postech-ami/FastMETRO) | 2022 | 1113 | 1114 | 1115 | 1116 | ### Segmentation 1117 | 1118 | - https://github.com/facebookresearch/MaskFormer 1119 | 1120 | | Title | Venue | Code | Year | 1121 | | :--------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------: | :-------------------------------------------------------------: | ---- | 1122 | | [Real-Time High-Resolution Background Matting](http://arxiv.org/abs/2012.07810) | arXiv:2012.07810 | [BackgroundMattingV2](https://github.com/PeterL1n/BackgroundMattingV2) | 2020 | 1123 | | [Robust High-Resolution Video Matting with Temporal Guidance](http://arxiv.org/abs/2108.11515) | ArXiv:2108.11515 [Cs] | [RobustVideoMatting](https://github.com/PeterL1n/RobustVideoMatting) | arXiv. 2021 | 1124 | 1125 | 1126 | 1127 | 1128 | ### Datasets 1129 | - https://github.com/karfly/human36m-camera-parameters 1130 | - https://github.com/deepimagination/TalkingHead-1KH 1131 | 1132 | | Title | Venue | Code | Year | 1133 | | :--------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------: | :-------------------------------------------------------------: | ---- | 1134 | | [Structured Local Radiance Fields for Human Avatar Modeling](http://arxiv.org/abs/2203.14478) | CVPR | [THUman4.0-Dataset](https://github.com/ZhengZerong/THUman4.0-Dataset) | 2022 | 1135 | | [Multiface: A Dataset for Neural Face Rendering](https://arxiv.org/abs/2207.11243v1) | ArXiv:2207.11243 [Cs.CV] | [multiface](https://github.com/facebookresearch/multiface) | 2022 | 1136 | | [ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representations](http://arxiv.org/abs/2203.14510) | CVPR | [ImFace](https://github.com/MingwuZheng/ImFace) | 2022 | 1137 | 1138 | 1139 | ### FLAME estimation 1140 | | Title | Venue | Code | Year | 1141 | | :--------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------: | :-------------------------------------------------------------: | ---- | 1142 | | [Towards Metrical Reconstruction of Human Faces](http://arxiv.org/abs/2204.06607) | ECCV | [MICA](https://github.com/Zielon/MICA) | arXiv. 2022 | 1143 | 1144 | ### Dog estimation 1145 | | Title | Venue | Code | Year | 1146 | | :--------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------: | :-------------------------------------------------------------: | ---- | 1147 | | [BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information] |CVPR | [barc_release](https://github.com/runa91/barc_release) | 2022 | 1148 | 1149 | 1150 | ### Panoptic 1151 | | Title | Venue | Code | Year | 1152 | | :--------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------: | :-------------------------------------------------------------: | ---- | 1153 | | [Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation](http://arxiv.org/abs/2203.15224) | ArXiv:2203.15224 [Cs] | [PanopticNeRF](https://github.com/fuxiao0719/PanopticNeRF) | arXiv. 2022 | 1154 | 1155 | 1156 | 1157 | ## SDF 1158 | 1159 | - https://github.com/facebookresearch/pifuhd 1160 | - https://github.com/pmneila/PyMCubes 1161 | 1162 | | Title | Venue | Code | Year | 1163 | | :------------------------------------------------------------------------------------------------------------------------------------ | :-------------------: | :----------------------------------------------------: | :--: | 1164 | | :white_check_mark: [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](http://arxiv.org/abs/1901.05103) | arXiv:1901.05103 [cs] | [DeepSDF](https://github.com/facebookresearch/DeepSDF) | 2019 | 1165 | | [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](http://arxiv.org/abs/1610.07584) | NeurIPS | | 2016 | 1166 | | [Occupancy Networks: Learning 3D Reconstruction in Function Space](http://arxiv.org/abs/1812.03828) | arXiv:1812.03828 [cs] | | 2019 | 1167 | | [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](http://arxiv.org/abs/1905.05172) | arXiv:1905.05172 [cs] | | 2019 | 1168 | | [Deep Meta Functionals for Shape Representation](http://arxiv.org/abs/1908.06277) | arXiv:1908.06277 [cs] | | 2019 | 1169 | 1170 | ### 3D 1171 | 1172 | | Title | Venue | Code | Year | 1173 | | :----------------------------------------------------------------------------------------------------------------------------------------- | :-------------------: | :----------------------------------------------------------: | :--: | 1174 | | [Escaping Plato’s Cave: 3D Shape From Adversarial Rendering](http://arxiv.org/abs/1811.11606) | ICCV | | 2019 | 1175 | | [StyleRig: Rigging StyleGAN for 3D Control over Portrait Images](http://arxiv.org/abs/2004.00121) | arXiv:2004.00121 [cs] | | 2020 | 1176 | | [Exemplar-Based 3D Portrait Stylization](http://arxiv.org/abs/2104.14559) | arXiv:2104.14559 [cs] | [github](https://github.com/halfjoe/3D-Portrait-Stylization) | 2021 | 1177 | | :heart: [Landmark Detection and 3D Face Reconstruction for Caricature Using a Nonlinear Parametric Model](http://arxiv.org/abs/2004.09190) | arXiv:2004.09190 [cs] | [CaricatureFace](https://github.com/Juyong/CaricatureFace) | 2021 | 1178 | | [SofGAN: A Portrait Image Generator with Dynamic Styling](http://arxiv.org/abs/2007.03780) | arXiv:2007.03780 [cs] | [sofgan](https://github.com/apchenstu/sofgan) | 2021 | 1179 | | :heart: [FreeStyleGAN: Free-View Editable Portrait Rendering with the Camera Manifold](http://arxiv.org/abs/2109.09378) | arXiv:2109.09378 [cs] | | 2021 | 1180 | | [PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering](http://arxiv.org/abs/2109.08379) | ICCV | [PIRender](https://github.com/RenYurui/PIRender) | 2021 | 1181 | 1182 | 1183 | 1184 | 1185 | ### Point Cloud 1186 | 1187 | | Title | Venue | Code | Year | 1188 | | :------------------------------------------------------------------------------------------------------------------------------------------------------------------ | :-------------------: | :--: | :--: | 1189 | | [Point-Based Modeling of Human Clothing](https://openaccess.thecvf.com/content/ICCV2021/html/Zakharkin_Point-Based_Modeling_of_Human_Clothing_ICCV_2021_paper.html) | ICCV | | 2021 | 1190 | | [ADOP: Approximate Differentiable One-Pixel Point Rendering](http://arxiv.org/abs/2110.06635) | arXiv:2110.06635 [cs] | | 2021 | 1191 | 1192 | ### Stylization 1193 | 1194 | | Title | Venue | Code | Year | 1195 | | :----------------------------------------------------------------- | :-------------------: | :---------------------------------------------------: | :--: | 1196 | | [Learning to Stylize Novel Views](http://arxiv.org/abs/2105.13509) | arXiv:2105.13509 [cs] | [stylescene](https://github.com/hhsinping/stylescene) | 2021 | 1197 | 1198 | ### Datasets 1199 | 1200 | - https://github.com/ofirkris/Faces-datasets 1201 | 1202 | | Title | Venue | Code | Year | 1203 | | :----------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------: | :------------------------------------------------------------------: | :--: | 1204 | | [Common Objects in 3D: Large-Scale Learning and Evaluation of Real-Life 3D Category Reconstruction](http://arxiv.org/abs/2109.00512) | ICCV | | 2021 | 1205 | | [A 3D Face Model for Pose and Illumination Invariant Face Recognition]() | IEEE International Conference on Advanced Video and Signal Based Surveillance | [BFM](https://faces.dmi.unibas.ch/bfm/main.php?nav=1-2&id=downloads) | 2009 | 1206 | | [SfSNet: Learning Shape, Reflectance and Illuminance of Faces in the Wild](http://arxiv.org/abs/1712.01261) | arXiv:1712.01261 [cs] | | 2018 | 1207 | 1208 | ### 3D-aware image synthesis (ref) 1209 | 1210 | | Title | Venue | Code | Year | 1211 | | :-------------------------------------------------------------------------------------------------------------- | :-------------------------: | :--: | :--: | 1212 | | [Visual Object Networks: Image Generation with Disentangled 3D Representation](http://arxiv.org/abs/1812.02725) | arXiv:1812.02725 [cs, stat] | | 2018 | 1213 | | [Escaping Plato’s Cave: 3D Shape From Adversarial Rendering](http://arxiv.org/abs/1811.11606) | ICCV | | 2019 | 1214 | | [HoloGAN: Unsupervised Learning of 3D Representations from Natural Images](http://arxiv.org/abs/1904.01326) | ICCV | | 2019 | 1215 | 1216 | ## Face 1217 | 1218 | ### Tools 1219 | 1220 | - https://github.com/wuhuikai/FaceSwap 1221 | - https://github.com/hysts/anime-face-detector 1222 | - https://github.com/qq775193759/3D-CariGAN 1223 | - https://github.com/yeemachine/kalidokit 1224 | - https://github.com/sicxu/Deep3DFaceRecon_pytorch 1225 | - https://github.com/happy-jihye/face-vid2vid-demo 1226 | 1227 | ### Edit 1228 | 1229 | | Title | Venue | Code | Year | 1230 | | :---------------------------------------------------------------------------------------------------------------------------------------- | :-------------------: | :--: | :--: | 1231 | | [FaceEraser: Removing Facial Parts for Augmented Reality](http://arxiv.org/abs/2109.10760) | arXiv:2109.10760 [cs] | | 2021 | 1232 | | [DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing](http://arxiv.org/abs/2109.10737) | arXiv:2109.10737 [cs] | | 2021 | 1233 | | :heart: [StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators](http://arxiv.org/abs/2108.00946) | arXiv:2108.00946 [cs] | | 2021 | 1234 | | [Beholder-GAN: Generation and Beautification of Facial Images with Conditioning on Their Beauty Level](http://arxiv.org/abs/1902.02593) | arXiv:1902.02593 [cs] | | 2019 | 1235 | | [Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks](http://arxiv.org/abs/2110.08398) | arXiv:2110.08398 [cs] | | 2021 | 1236 | | [Fine-Grained Control of Artistic Styles in Image Generation](http://arxiv.org/abs/2110.10278) | arXiv:2110.10278 [cs] | | 2021 | 1237 | 1238 | ### Anime Face 1239 | 1240 | - https://github.com/Sxela/ArcaneGAN 1241 | - https://github.com/mchong6/GANsNRoses 1242 | - https://github.com/FilipAndersson245/cartoon-gan 1243 | - https://github.com/venture-anime/cartoongan-pytorch 1244 | 1245 | | Title | Venue | Code | Year | 1246 | | :----------------------------------------------------------------------------------------------------------------------------- | :-------------------------: | :-------------------------------------------------------------------------------------: | :--: | 1247 | | [AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation](http://arxiv.org/abs/2102.12593) | arXiv:2102.12593 [cs] | | 2021 | 1248 | | [AnimeGAN: A Novel Lightweight GAN for Photo Animation] | | [AnimeGANv2](https://github.com/TachibanaYoshino/AnimeGANv2) | 2020 | 1249 | | :heart: [Learning to Cartoonize Using White-Box Cartoon Representations](https://ieeexplore.ieee.org/document/9157493/) | CVPR | [White-box-Cartoonization](https://github.com/SystemErrorWang/White-box-Cartoonization) | 2020 | 1250 | | [Generative Adversarial Networks for Photo to Hayao Miyazaki Style Cartoons](http://arxiv.org/abs/2005.07702) | arXiv:2005.07702 [cs, eess] | | 2020 | 1251 | 1252 | ### 3DMM 1253 | 1254 | - https://github.com/lattas/AvatarMe 1255 | 1256 | | Title | Venue | Code | Year | 1257 | | :--------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------: | :----: | :-------------------------------------------------------------: | 1258 | | [A Morphable Model for the Synthesis of 3D Faces](https://doi.org/10.1145/311535.311556) | Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques | [3DMM] | SIGGRAPH ’99, USA: ACM Press/Addison-Wesley Publishing Co. 1999 | 1259 | 1260 | ### Face 1261 | 1262 | | Title | Venue | Code | Year | 1263 | | :----------------------------------------------------------------------------------------- | :-------------------: | :--: | :--: | 1264 | | [SketchHairSalon: Deep Sketch-Based Hair Image Synthesis](http://arxiv.org/abs/2109.07874) | arXiv:2109.07874 [cs] | | 2021 | 1265 | 1266 | ### Face Alignment 1267 | 1268 | | Title | Venue | Code | Year | 1269 | | :--------------------------------------------------- | :------------------------------------------------------------: | :--: | :--: | 1270 | | [Face Alignment Across Large Poses: A 3D Solution]() | IEEE Transactions on Pattern Analysis and Machine Intelligence | | 2019 | 1271 | 1272 | ### Face Recognition 1273 | 1274 | | Title | Venue | Code | Year | 1275 | | :----------------------------------------------------------------------------------- | :--------------------------------------------------------------------: | :--: | :--: | 1276 | | [High-Fidelity Pose and Expression Normalization for Face Recognition in the Wild]() | 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) | | 2015 | 1277 | 1278 | ### Face swapping 1279 | 1280 | - https://github.com/mindslab-ai/hififace 1281 | 1282 | ## 3D 1283 | 1284 | | Title | Venue | Code | Year | 1285 | | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------------: | :----------------------------------------------------------: | :--: | 1286 | | [Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild](http://arxiv.org/abs/1911.11130) | arXiv:1911.11130 [cs] | [unsup3d](https://github.com/elliottwu/unsup3d) | 2020 | 1287 | | [Do 2D GANs Know 3D Shape? Unsupervised 3D Shape Reconstruction from 2D Image GANs](http://arxiv.org/abs/2011.00844) | arXiv:2011.00844 [cs] | [GAN2Shape](https://github.com/XingangPan/GAN2Shape) | 2021 | 1288 | | [A Geometric Analysis of Deep Generative Image Models and Its Applications](https://openreview.net/forum?id=GH7QRzUDdXG) | ICLR | | 2021 | 1289 | | [Lifting 2D StyleGAN for 3D-Aware Face Generation](http://arxiv.org/abs/2011.13126) | CVPR | [LiftedGAN](https://github.com/seasonSH/LiftedGAN) | 2021 | 1290 | | [Image GANs Meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering](http://arxiv.org/abs/2010.09125) | arXiv:2010.09125 [cs] | | 2021 | 1291 | | [Neural 3D Mesh Renderer](http://arxiv.org/abs/1711.07566) | CVPR | | 2018 | 1292 | | [Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction](http://arxiv.org/abs/2105.07474) | arXiv:2105.07474 [cs] | | 2021 | 1293 | | [Inverting Generative Adversarial Renderer for Face Reconstruction](http://arxiv.org/abs/2105.02431) | CVPR | [StyleRenderer](https://github.com/WestlyPark/StyleRenderer) | 2021 | 1294 | | [Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collection](http://arxiv.org/abs/2106.07852) | arXiv:2106.07852 [cs] | | 2021 | 1295 | | [Subdivision-Based Mesh Convolution Networks](http://arxiv.org/abs/2106.02285) | arXiv:2106.02285 [cs] | | 2021 | 1296 | | [Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collection](http://arxiv.org/abs/2106.07852) | CVPR | | 2021 | 1297 | | [To Fit or Not to Fit: Model-Based Face Reconstruction and Occlusion Segmentation from Weak Supervision](http://arxiv.org/abs/2106.09614) | arXiv:2106.09614 [cs] | | 2021 | 1298 | | [Unsupervised Learning of Depth and Depth-of-Field Effect from Natural Images with Aperture Rendering Generative Adversarial Networks](http://arxiv.org/abs/2106.13041) | arXiv:2106.13041 [cs, eess, stat] | | 2021 | 1299 | | [DOVE: Learning Deformable 3D Objects by Watching Videos](http://arxiv.org/abs/2107.10844) | arXiv:2107.10844 [cs] | | 2021 | 1300 | | [De-Rendering the World’s Revolutionary Artefacts](http://arxiv.org/abs/2104.03954) | CVPR | | 2021 | 1301 | | [Learning Generative Models of Textured 3D Meshes from Real-World Images](http://arxiv.org/abs/2103.15627) | ICCV | | 2021 | 1302 | | [Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images](http://arxiv.org/abs/2109.02288) | ICCV | | 2021 | 1303 | 1304 | ## DA 1305 | 1306 | | Title | Venue | Code | Year | 1307 | | :--------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------: | :--: | :--: | 1308 | | [Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignment](http://arxiv.org/abs/2106.02845) | arXiv:2106.02845 [cs] | | 2021 | 1309 | | [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](http://arxiv.org/abs/2101.10979) | arXiv:2101.10979 [cs] | | 2021 | 1310 | 1311 | ## Data 1312 | 1313 | - https://github.com/koaning/doubtlab 1314 | 1315 | | Title | Venue | Code | Year | 1316 | | :----------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------: | :--: | :--: | 1317 | | :white_check_mark: [Semi-Supervised Active Learning with Temporal Output Discrepancy](http://arxiv.org/abs/2107.14153) | ICCV | | 2021 | 1318 | | :heart: [Mean Teachers Are Better Role Models: Weight-Averaged Consistency Targets Improve Semi-Supervised Deep Learning Results](http://arxiv.org/abs/1703.01780) | NeurIPS | | 2017 | 1319 | | [When Deep Learners Change Their Mind: Learning Dynamics for Active Learning](http://arxiv.org/abs/2107.14707) | arXiv:2107.14707 [cs] | | 2021 | 1320 | | [On The State of Data In Computer Vision: Human Annotations Remain Indispensable for Developing Deep Learning Models](http://arxiv.org/abs/2108.00114) | arXiv:2108.00114 [cs] | | 2021 | 1321 | | [StyleAugment: Learning Texture De-Biased Representations by Style Augmentation without Pre-Defined Textures](http://arxiv.org/abs/2108.10549) | arXiv:2108.10549 [cs] | | 2021 | 1322 | | [Multi-Task Self-Training for Learning General Representations](http://arxiv.org/abs/2108.11353) | ICCV | | 2021 | 1323 | | [OOWL500: Overcoming Dataset Collection Bias in the Wild](http://arxiv.org/abs/2108.10992) | arXiv:2108.10992 [cs] | | 2021 | 1324 | | [Ghost Loss to Question the Reliability of Training Data]() | IEEE Access | | 2020 | 1325 | | [Revisiting 3D ResNets for Video Recognition](http://arxiv.org/abs/2109.01696) | arXiv:2109.01696 [cs, eess] | | 2021 | 1326 | | :heart: [Revisiting ResNets: Improved Training and Scaling Strategies](http://arxiv.org/abs/2103.07579) | arXiv:2103.07579 [cs] | | 2021 | 1327 | | [Learning Fast Sample Re-Weighting Without Reward Data](http://arxiv.org/abs/2109.03216) | ICCV | | 2021 | 1328 | | [How Important Is Importance Sampling for Deep Budgeted Training?](http://arxiv.org/abs/2110.14283) | arXiv:2110.14283 [cs] | | 2021 | 1329 | 1330 | ## CNN & BN 1331 | 1332 | ### Light architecture 1333 | 1334 | - https://github.com/yoshitomo-matsubara/torchdistill 1335 | - https://github.com/milesial/Pytorch-UNet 1336 | 1337 | | Title | Venue | Code | Year | 1338 | | :----------------------------------------------------------------------------------------------------------------------------------- | :-------------------: | :--: | :--: | 1339 | | [Network Augmentation for Tiny Deep Learning](http://arxiv.org/abs/2110.08890) | arXiv:2110.08890 [cs] | | 2021 | 1340 | | [Non-Deep Networks](http://arxiv.org/abs/2110.07641) | arXiv:2110.07641 [cs] | | 2021 | 1341 | | [When to Prune? A Policy towards Early Structural Pruning](http://arxiv.org/abs/2110.12007) | arXiv:2110.12007 [cs] | | 2021 | 1342 | | :heart: [ConformalLayers: A Non-Linear Sequential Neural Network with Associative Layers](http://arxiv.org/abs/2110.12108) | arXiv:2110.12108 [cs] | | 2021 | 1343 | | [CHIP: CHannel Independence-Based Pruning for Compact Neural Networks](http://arxiv.org/abs/2110.13981) | arXiv:2110.13981 [cs] | | 2021 | 1344 | | [Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training](http://arxiv.org/abs/2102.02887) | arXiv:2102.02887 [cs] | | 2021 | 1345 | 1346 | ### Antialiased CNNs 1347 | 1348 | | Title | Venue | Code | Year | 1349 | | :----------------------------------------------------------------------------------------------- | :-------------------: | :--: | :---------: | 1350 | | [Making Convolutional Networks Shift-Invariant Again](http://arxiv.org/abs/1904.11486) | arXiv:1904.11486 [cs] | | 2019 | 1351 | | [Group Equivariant Convolutional Networks](http://arxiv.org/abs/1602.07576) | ICML | | arXiv. 2016 | 1352 | | [Harmonic Networks: Deep Translation and Rotation Equivariance](http://arxiv.org/abs/1612.04642) | CVPR | | arXiv. 2017 | 1353 | | [Learning Steerable Filters for Rotation Equivariant CNNs](http://arxiv.org/abs/1711.07289) | CVPR | | arXiv. 2018 | 1354 | 1355 | ### Architecture 1356 | 1357 | | Title | Venue | Code | Year | 1358 | | :-------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------: | :------------------------------------------------------: | :--: | 1359 | | [Beyond BatchNorm: Towards a General Understanding of Normalization in Deep Learning](http://arxiv.org/abs/2106.05956) | arXiv:2106.05956 [cs] | | 2021 | 1360 | | [R-Drop: Regularized Dropout for Neural Networks](http://arxiv.org/abs/2106.14448) | arXiv:2106.14448 [cs] | | 2021 | 1361 | | [Switchable Whitening for Deep Representation Learning](http://arxiv.org/abs/1904.09739) | ICCV | | 2019 | 1362 | | [Positional Normalization](http://arxiv.org/abs/1907.04312) | arXiv:1907.04312 [cs] | | 2019 | 1363 | | [On Feature Normalization and Data Augmentation](http://arxiv.org/abs/2002.11102) | arXiv:2002.11102 [cs, stat] | | 2021 | 1364 | | [Channel Equilibrium Networks for Learning Deep Representation](http://arxiv.org/abs/2003.00214) | arXiv:2003.00214 [cs] | | 2020 | 1365 | | [Representative Batch Normalization with Feature Calibration]() | CVPR | | 2021 | 1366 | | [EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural Network](http://arxiv.org/abs/2105.14447) | arXiv:2105.14447 [cs] | | 2021 | 1367 | | [Bias Loss for Mobile Neural Networks](http://arxiv.org/abs/2107.11170) | arXiv:2107.11170 [cs] | | 2021 | 1368 | | [Compositional Models: Multi-Task Learning and Knowledge Transfer with Modular Networks](http://arxiv.org/abs/2107.10963) | arXiv:2107.10963 [cs] | | 2021 | 1369 | | [Log-Polar Space Convolution for Convolutional Neural Networks](http://arxiv.org/abs/2107.11943) | arXiv:2107.11943 [cs] | | 2021 | 1370 | | [Decoupled Dynamic Filter Networks](http://arxiv.org/abs/2104.14107) | arXiv:2104.14107 [cs] | | 2021 | 1371 | | [Spectral Leakage and Rethinking the Kernel Size in CNNs](http://arxiv.org/abs/2101.10143) | arXiv:2101.10143 [cs] | | 2021 | 1372 | | [Learning with Noisy Labels via Sparse Regularization](http://arxiv.org/abs/2108.00192) | ICCV | | 2021 | 1373 | | :heart: [Impact of Aliasing on Generalization in Deep Convolutional Networks](http://arxiv.org/abs/2108.03489) | ICCV | | 2021 | 1374 | | [Orthogonal Over-Parameterized Training](http://arxiv.org/abs/2004.04690) | CVPR | | 2021 | 1375 | | [Multiplying Matrices Without Multiplying](http://arxiv.org/abs/2106.10860) | ICML | | 2021 | 1376 | | [AASeg: Attention Aware Network for Real Time Semantic Segmentation](http://arxiv.org/abs/2108.04349) | arXiv:2108.04349 [cs, eess] | | 2021 | 1377 | | [MicroNet: Improving Image Recognition with Extremely Low FLOPs](http://arxiv.org/abs/2108.05894) | ICCV | | 2021 | 1378 | | [Contextual Convolutional Neural Networks](http://arxiv.org/abs/2108.07387) | arXiv:2108.07387 [cs] | | 2021 | 1379 | | [Torch.Manual_seed(3407) Is All You Need: On the Influence of Random Seeds in Deep Learning Architectures for Computer Vision](http://arxiv.org/abs/2109.08203) | arXiv:2109.08203 [cs] | | 2021 | 1380 | | [KATANA: Simple Post-Training Robustness Using Test Time Augmentations](http://arxiv.org/abs/2109.08191) | arXiv:2109.08191 [cs] | | 2021 | 1381 | | [Global Pooling, More than Meets the Eye: Position Information Is Encoded Channel-Wise in CNNs](http://arxiv.org/abs/2108.07884) | ICCV | | 2021 | 1382 | | :white_check_mark: [A ConvNet for the 2020s](http://arxiv.org/abs/2201.03545) | arXiv:2201.03545 [cs] | [ConvNeXt](https://github.com/facebookresearch/ConvNeXt) | 2022 | 1383 | 1384 | ### Compression 1385 | 1386 | | Title | Venue | Code | Year | 1387 | | :------------------------------------------------------------------------------------------------------- | :-------------------: | :--: | :--: | 1388 | | [AdaPruner: Adaptive Channel Pruning and Effective Weights Inheritance](http://arxiv.org/abs/2109.06397) | arXiv:2109.06397 [cs] | | 2021 | 1389 | 1390 | ### Detection 1391 | 1392 | | Title | Venue | Code | Year | 1393 | | :--------------------------------------------------------------------------------------------------------- | :-------------------: | :--: | :--: | 1394 | | [Anchor DETR: Query Design for Transformer-Based Detector](http://arxiv.org/abs/2109.07107) | arXiv:2109.07107 [cs] | | 2021 | 1395 | | :heart: [Detecting Twenty-Thousand Classes Using Image-Level Supervision](http://arxiv.org/abs/2201.02605) | arXiv:2201.02605 [cs] | | 2022 | 1396 | 1397 | ### Segmentation 1398 | 1399 | - https://github.com/xuebinqin/U-2-Net#usage-for-portrait-generation 1400 | 1401 | | Title | Venue | Code | Year | 1402 | | :-------------------------------------------------------------- | :----------------------: | :--: | :--: | 1403 | | [Robust High-Resolution Video Matting with Temporal Guidance]() | arXiv:2108.11515 [cs.CV] | | 2021 | 1404 | 1405 | ### MLP 1406 | 1407 | | Title | Venue | Code | Year | 1408 | | :-------------------------------------------------------------------------------------------------------------------- | :----------------------: | :--: | :--: | 1409 | | [ResMLP: Feedforward Networks for Image Classification with Data-Efficient Training](http://arxiv.org/abs/2105.03404) | arXiv:2105.03404 [cs] | | 2021 | 1410 | | [ConvMLP: Hierarchical Convolutional MLPs for Vision](http://arxiv.org/abs/2109.04454) | arXiv:2109.04454 [cs] | | 2021 | 1411 | | [A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP]() | arXiv:2108.13002 [cs.CV] | | 2021 | 1412 | | [Sparse-MLP: A Fully-MLP Architecture with Conditional Computation](http://arxiv.org/abs/2109.02008) | arXiv:2109.02008 [cs] | | 2021 | 1413 | | [MLP-Mixer: An All-MLP Architecture for Vision](https://arxiv.org/abs/2105.01601v1) | 2021 | 1414 | | [CycleMLP: A MLP-like Architecture for Dense Prediction](http://arxiv.org/abs/2107.10224) | ICLR | | 2022 | 1415 | 1416 | ### Transformer 1417 | 1418 | - https://github.com/xxxnell/how-do-vits-work 1419 | - https://github.com/hamidkazemi22/vit-visualization 1420 | 1421 | | Title | Venue | Code | Year | 1422 | | :----------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------: | :----------------------------------------------: | :--: | 1423 | | [Training Data-Efficient Image Transformers & Distillation through Attention](http://arxiv.org/abs/2012.12877) | arXiv:2012.12877 [cs] | [deit](https://github.com/facebookresearch/deit) | 2020 | 1424 | | [Intriguing Properties of Vision Transformers](http://arxiv.org/abs/2105.10497) | arXiv:2105.10497 [cs] | | 2021 | 1425 | | [CogView: Mastering Text-to-Image Generation via Transformers](http://arxiv.org/abs/2105.13290) | arXiv:2105.13290 [cs] | | 2021 | 1426 | | [An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale](http://arxiv.org/abs/2010.11929) | arXiv:2010.11929 [cs] | | 2021 | 1427 | | [Scaling Vision Transformers](http://arxiv.org/abs/2106.04560) | arXiv:2106.04560 [cs] | | 2021 | 1428 | | [IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers](http://arxiv.org/abs/2106.12620) | arXiv:2106.12620 [cs] | | 2021 | 1429 | | [Rethinking and Improving Relative Position Encoding for Vision Transformer]() | ICCV | | 2021 | 1430 | | [Go Wider Instead of Deeper](http://arxiv.org/abs/2107.11817) | arXiv:2107.11817 [cs] | | 2021 | 1431 | | [A Unified Efficient Pyramid Transformer for Semantic Segmentation](http://arxiv.org/abs/2107.14209) | arXiv:2107.14209 [cs] | | 2021 | 1432 | | :heart: [Conditional DETR for Fast Training Convergence](http://arxiv.org/abs/2108.06152) | ICCV | | 2021 | 1433 | | :heart: [Sketch Your Own GAN](http://arxiv.org/abs/2108.02774) | ICCV | | 2021 | 1434 | | [CrossFormer: A Versatile Vision Transformer Based on Cross-Scale Attention](http://arxiv.org/abs/2108.00154) | arXiv:2108.00154 [cs] | | 2021 | 1435 | | [Uformer: A General U-Shaped Transformer for Image Restoration](http://arxiv.org/abs/2106.03106) | arXiv:2106.03106 [cs] | | 2021 | 1436 | | [ConvNets vs. Transformers: Whose Visual Representations Are More Transferable?](http://arxiv.org/abs/2108.05305) | arXiv:2108.05305 [cs] | | 2021 | 1437 | | [Mobile-Former: Bridging MobileNet and Transformer](http://arxiv.org/abs/2108.05895) | arXiv:2108.05895 [cs] | | 2021 | 1438 | | [SOTR: Segmenting Objects with Transformers](http://arxiv.org/abs/2108.06747) | ICCV | | 2021 | 1439 | | [Video Transformer Network](http://arxiv.org/abs/2102.00719) | arXiv:2102.00719 [cs] | | 2021 | 1440 | | [Do Vision Transformers See Like Convolutional Neural Networks?](http://arxiv.org/abs/2108.08810) | arXiv:2108.08810 [cs, stat] | | 2021 | 1441 | | [UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-Wise Perspective with Transformer](http://arxiv.org/abs/2109.04335) | arXiv:2109.04335 [cs, eess] | | 2021 | 1442 | | [$\infty$-Former: Infinite Memory Transformer](http://arxiv.org/abs/2109.00301) | arXiv:2109.00301 [cs] | | 2021 | 1443 | | [PnP-DETR: Towards Efficient Visual Analysis with Transformers](http://arxiv.org/abs/2109.07036) | ICCV | | 2021 | 1444 | | [MobileViT: Light-Weight, General-Purpose, and Mobile-Friendly Vision Transformer](http://arxiv.org/abs/2110.02178) | arXiv:2110.02178 [cs] | | 2021 | 1445 | | [MetaFormer Is Actually What You Need for Vision](http://arxiv.org/abs/2111.11418) | arXiv:2111.11418 [cs] | | 2021 | 1446 | | [Restormer: Efficient Transformer for High-Resolution Image Restoration](http://arxiv.org/abs/2111.09881) | arXiv:2111.09881 [cs] | [Restormer](https://github.com/swz30/Restormer) | 2021 | 1447 | | :white_check_mark: [An Empirical Study of Training Self-Supervised Vision Transformers](http://arxiv.org/abs/2104.02057) | arXiv:2104.02057 [cs] | | 2021 | 1448 | | :white_check_mark: [When Vision Transformers Outperform ResNets without Pre-Training or Strong Data Augmentations](https://arxiv.org/abs/2106.01548v2) | arXiv:2106.01548 [cs.CV] | | 2021 | 1449 | | [Visual Attention Network](http://arxiv.org/abs/2202.09741) | arXiv:2202.09741 [cs] | | 2022 | 1450 | 1451 | ### ssl 1452 | 1453 | - https://github.com/ucasligang/awesome-MIM 1454 | 1455 | | Title | Venue | Code | Year | 1456 | | :-------------------------------------------------------------------------------------------------------------------------- | :-------------------: | :--------------------------------------------------------: | :--: | 1457 | | [Emerging Properties in Self-Supervised Vision Transformers](http://arxiv.org/abs/2104.14294) | arXiv:2104.14294 [cs] | [dino](https://github.com/facebookresearch/dino) | 2021 | 1458 | | [What Is Considered Complete for Visual Recognition?](http://arxiv.org/abs/2105.13978) | arXiv:2105.13978 [cs] | | 2021 | 1459 | | [On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals](http://arxiv.org/abs/2107.14762) | arXiv:2107.14762 [cs] | | 2021 | 1460 | | :heart: [Improving Contrastive Learning by Visualizing Feature Transformation](http://arxiv.org/abs/2108.02982) | ICCV | | 2021 | 1461 | | [Scale Efficiently: Insights from Pre-Training and Fine-Tuning Transformers](http://arxiv.org/abs/2109.10686) | arXiv:2109.10686 [cs] | | 2021 | 1462 | | [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](http://arxiv.org/abs/2110.08263) | arXiv:2110.08263 [cs] | | 2021 | 1463 | | [BEiT: BERT Pre-Training of Image Transformers](http://arxiv.org/abs/2106.08254) | arXiv:2106.08254 [cs] | | 2021 | 1464 | | :heart: [Parametric Contrastive Learning](http://arxiv.org/abs/2107.12028) | ICCV | | 2021 | 1465 | | :heart: [ImageNet-21K Pretraining for the Masses](http://arxiv.org/abs/2104.10972) | NeurIPS | [ImageNet21K](https://github.com/Alibaba-MIIL/ImageNet21K) | 2021 | 1466 | | :heart: [ML-Decoder: Scalable and Versatile Classification Head](http://arxiv.org/abs/2111.12933) | arXiv:2111.12933 [cs] | [ML_Decoder](https://github.com/Alibaba-MIIL/ML_Decoder) | 2021 | 1467 | | [Asymmetric Loss For Multi-Label Classification](http://arxiv.org/abs/2009.14119) | ICCV | [ASL](https://github.com/Alibaba-MIIL/ASL) | 2021 | 1468 | | [Grounded Language-Image Pre-Training](http://arxiv.org/abs/2112.03857) | arXiv:2112.03857 [cs] | | 2021 | 1469 | 1470 | ## Finetune 1471 | 1472 | | Title | Venue | Code | Year | 1473 | | :----------------------------------------------------------------------------------------------- | :------------------: | :--: | :--: | 1474 | | :heart: [How Transferable Are Features in Deep Neural Networks?](http://arxiv.org/abs/1411.1792) | arXiv:1411.1792 [cs] | | 2014 | 1475 | 1476 | ## Positional Encoding 1477 | 1478 | | Title | Venue | Code | Year | 1479 | | :------------------------------------------------------------------------------------------------------------------------------- | :-------------------------: | :--: | :--: | 1480 | | [Positional Encoding as Spatial Inductive Bias in GANs](http://arxiv.org/abs/2012.05217) | arXiv:2012.05217 [cs] | | 2020 | 1481 | | [Mind the Pad -- CNNs Can Develop Blind Spots](http://arxiv.org/abs/2010.02178) | arXiv:2010.02178 [cs, stat] | | 2020 | 1482 | | :heart: [How Much Position Information Do Convolutional Neural Networks Encode?](http://arxiv.org/abs/2001.08248) | ICLR | | 2020 | 1483 | | [On Translation Invariance in CNNs: Convolutional Layers Can Exploit Absolute Spatial Location](http://arxiv.org/abs/2003.07064) | CVPR | | 2020 | 1484 | | [Rethinking and Improving Relative Position Encoding for Vision Transformer]() | ICCV | | 2021 | 1485 | | [A Structured Dictionary Perspective on Implicit Neural Representations](http://arxiv.org/abs/2112.01917) | arXiv:2112.01917 [cs] | | 2021 | 1486 | 1487 | ## NAS 1488 | 1489 | ### NAS cls 1490 | 1491 | | Title | Venue | Code | Year | 1492 | | :---------------------------------------------------------------------------------------------------- | :---: | :--: | :--: | 1493 | | [Neural Architecture Search with Reinforcement Learning](https://arxiv.org/abs/1611.01578v2) | ICLR | | 2017 | 1494 | | [Learning Transferable Architectures for Scalable Image Recognition](http://arxiv.org/abs/1707.07012) | CVPR | | 2018 | 1495 | | [Progressive Neural Architecture Search](http://arxiv.org/abs/1712.00559) | ECCV | | 2018 | 1496 | | [Efficient Neural Architecture Search via Parameter Sharing](http://arxiv.org/abs/1802.03268) | ICML | | 2018 | 1497 | | [MnasNet: Platform-Aware Neural Architecture Search for Mobile](http://arxiv.org/abs/1807.11626) | CVPR | | 2019 | 1498 | | [DARTS: Differentiable Architecture Search](http://arxiv.org/abs/1806.09055) | ICLR | | 2019 | 1499 | 1500 | ### NAS GAN 1501 | 1502 | | Title | Venue | Code | Year | 1503 | | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------: | :--: | :--: | 1504 | | [AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks]() | IEEE Transactions on Pattern Analysis and Machine Intelligence | | 2021 | 1505 | | [GAN Compression: Efficient Architectures for Interactive Conditional GANs](http://openaccess.thecvf.com/content_CVPR_2020/html/Li_GAN_Compression_Efficient_Architectures_for_Interactive_Conditional_GANs_CVPR_2020_paper.html) | CVPR | | 2020 | 1506 | | [Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search](http://arxiv.org/abs/2007.09180) | ECCV | | 2020 | 1507 | | [AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks](http://arxiv.org/abs/2006.08198) | ICML | | 2020 | 1508 | | [A Multi-Objective Architecture Search for Generative Adversarial Networks](https://doi.org/10.1145/3377929.3390004) | | | 2020 | 1509 | | [AutoGAN: Neural Architecture Search for Generative Adversarial Networks](http://arxiv.org/abs/1908.03835) | ICCV | | 2019 | 1510 | 1511 | ## Low-level 1512 | 1513 | ### Super-resolution 1514 | 1515 | - https://github.com/nihui/realsr-ncnn-vulkan 1516 | 1517 | ### Frame Interpolation 1518 | 1519 | | Title | Venue | Code | Year | 1520 | | :---------------------------------------------------------------------------- | :-------------------: | :--: | :--: | 1521 | | [FILM: Frame Interpolation for Large Motion](http://arxiv.org/abs/2202.04901) | arXiv:2202.04901 [cs] | | 2022 | 1522 | 1523 | ### Denoising 1524 | 1525 | | Title | Venue | Code | Year | 1526 | | :------------------------------------------------------------------------------- | :-----------------------------------: | :-------------------------------------------: | :--: | 1527 | | [Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering]() | IEEE Transactions on Image Processing | | 2007 | 1528 | | [Towards Flexible Blind JPEG Artifacts Removal](http://arxiv.org/abs/2109.14573) | arXiv:2109.14573 [cs, eess] | [FBCNN](https://github.com/jiaxi-jiang/FBCNN) | 2021 | 1529 | 1530 | 1531 | ## Scholar 1532 | 1533 | - https://github.com/tangjiapeng 1534 | - [Fisher Yu](https://www.yf.io/) 1535 | --------------------------------------------------------------------------------