└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Learned-Data-Compression 2 | A collection of papers related to data compression. 3 | 4 | ## Overview 5 | [AAAI 2025](#AAAI2025), [ICLR 2025](#ICLR2025), [CVPR 2025](#CVPR2025), [ICML 2025](#ICML2025) 6 | 7 | [ICLR 2024](#ICLR2024), [CVPR 2024](#CVPR2024), [ICML 2024](#ICML2024), [ECCV 2024](#ECCV2024), [ACMMM 2024](#ACMMM2024), [NeurIPS 2024](#NeurIPS2024), [AAAI 2024](#AAAI2024), 8 | 9 | [ICLR 2023](#ICLR2023), [ICML 2023](#ICML2023), [NeurIPS 2023](#NeurIPS2023), [AAAI 2023](#AAAI2023), [ICCV 2023](#ICCV2023), [CVPR 2023](#CVPR2023), [ACMMM 2023](#ACMMM2023), 10 | 11 | [IEEE TPAMI](#TPAMI), [IEEE TCSVT](#TCSVT), [IEEE TIP](#TIP), [IEEE TMM](#TMM), 12 | 13 | [Other](#other) 14 | 15 | 16 | ## ICML 2025 17 | **Synonymous Variational Inference for Perceptual Image Compression.** [Paper](https://arxiv.org/pdf/2505.22438) 18 | 19 | **Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion.** [Paper](https://arxiv.org/pdf/2505.08281); [Code](https://github.com/NJUVISION/ResULIC) 20 | 21 | 22 | ## CVPR 2025 23 | **Neural Video Compression with Context Modulation.** [Paper](https://arxiv.org/pdf/2505.14541) 24 | 25 | **High Dynamic Range Video Compression: A Large-Scale Benchmark Dataset and A Learned Bit-depth Scalable Compression Algorithm.** [Paper] 26 | 27 | **PICD: Versatile Perceptual Image Compression with Diffusion Rendering.** [Paper](https://arxiv.org/pdf/2505.05853) 28 | 29 | **Learned Image Compression with Dictionary-based Entropy Model.** [Paper](https://arxiv.org/pdf/2504.00496); [Code](https://github.com/labshuhanggu/dcae) 30 | 31 | **Multirate Neural Image Compression with Adaptive Lattice Vector Quantization.** [Paper] 32 | 33 | **Test-Time Fine-Tuning of Image Compression Models for Multi-Task Adaptability.** [Paper] 34 | 35 | **MambaIC: State Space Models for High-Performance Learned Image Compression.** [Paper](https://arxiv.org/pdf/2503.12461) 36 | 37 | **ECVC: Exploiting Non-Local Correlations in Multiple Frames for Contextual Video Compression.** [Paper](https://arxiv.org/pdf/2410.09706); [Code](https://github.com/JiangWeibeta/ECVC) 38 | 39 | **Balanced Rate-Distortion Optimization in Learned Image Compression.** [Paper](https://arxiv.org/pdf/2502.20161) 40 | 41 | **Extremely low-bitrate Image Compression Semantically Disentangled by LMMs from a Human Perception Perspective.** [Paper](https://arxiv.org/pdf/2503.00399) 42 | 43 | **Towards Practical Real-Time Neural Video Compression.** [Paper](https://arxiv.org/pdf/2502.20762) 44 | 45 | 46 | ## ICLR 2025 47 | **Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaption.** [Paper](https://arxiv.org/pdf/2406.00758) 48 | 49 | **Fast Feedforward 3D Gaussian Splatting Compression.** [Paper](https://openreview.net/attachment?id=DCandSZ2F1&name=pdf) 50 | 51 | **Locality-aware Gaussian Compression for Fast and High-quality Rendering.** [Paper](https://openreview.net/attachment?id=dHYwfV2KeP&name=pdf) 52 | 53 | **An Exploration with Entropy Constrained 3D Gaussians for 2D Video Compression.** [Paper](https://openreview.net/attachment?id=JbRM5QKRDd&name=pdf); [Code](https://github.com/actcwlf/GSVC) 54 | 55 | **Scaling Transformers for Low-bitrate High-quality Speech Coding.** [Paper](https://openreview.net/attachment?id=4YpMrGfldX&name=pdf) 56 | 57 | **Resolution Attack: Exploiting Image Compression to Deceive Deep Neural Networks.** [Paper](https://openreview.net/attachment?id=OFukl9Qg8P&name=pdf) 58 | 59 | **FlowDec: A Flow-based Full-band General Audio Codec with High Perceptual Quality.** [Paper](https://openreview.net/attachment?id=uxDFlPGRLX&name=pdf) 60 | 61 | **Lossy Compression with Pretrained Diffusion Models.** [Paper](https://openreview.net/attachment?id=raUnLe0Z04&name=pdf) 62 | 63 | **On Quantizing Neural Representation For Variable-Rate Video Coding.** [Paper](https://openreview.net/attachment?id=44cMlQSreK&name=pdf) 64 | 65 | **Progressive Compression with Universally Quantized Diffusion Models.** [Paper](https://openreview.net/attachment?id=CxXGvKRDnL&name=pdf) 66 | 67 | **CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compression.** [Paper](https://arxiv.org/abs/2503.00357) 68 | 69 | **On Disentangled Training for Nonlinear Transform in Learned Image Compression.** [Paper](https://arxiv.org/pdf/2501.13751); [Code](https://github.com/qingshi9974/AuxT) 70 | 71 | 72 | ## AAAI 2025 73 | **PNVC: Towards Practical INR-based Video Compression.** [Paper](https://ojs.aaai.org/index.php/AAAI/article/view/32315) 74 | 75 | **Conditional Latent Coding with Learnable Synthesized Reference for Deep Image Compression (Oral).** [Paper](https://arxiv.org/pdf/2502.09971); [Code](https://github.com/ydchen0806/CLC) 76 | 77 | **Large Images are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian Splatting.** [Paper](https://arxiv.org/pdf/2502.09039) 78 | 79 | **Towards Loss-Resilient Image Coding for Unstable Satellite Networks.** [Paper](https://arxiv.org/pdf/2501.11263) 80 | 81 | **CALLIC: Content Adaptive Learning for Lossless Image Compression.** [Paper](https://arxiv.org/pdf/2412.17464) 82 | 83 | **Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression.** [Paper](https://arxiv.org/pdf/2412.11379) 84 | 85 | 86 | ## AAAI 2024 87 | **Deep Hierarchical Video Compression.** [Paper](https://ojs.aaai.org/index.php/AAAI/article/view/28733); [Code](https://github.com/NJUVISION/DHVC); [Journal Version](https://arxiv.org/pdf/2410.02598) 88 | 89 | **Offline and Online Optical Flow Enhancement for Deep Video Compression.** [Paper](https://ojs.aaai.org/index.php/AAAI/article/view/28317) 90 | 91 | 92 | ## NeurIPS 2024 93 | **NVRC: Neural Video Representation Compression.** [Paper](https://openreview.net/attachment?id=I29aiMdm4u&name=pdf) 94 | 95 | **Robustly overfitting latents for flexible neural image compression.** [Paper](https://openreview.net/attachment?id=NQB9myZksw&name=pdf) 96 | 97 | **Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression.** [Paper](https://openreview.net/attachment?id=dLr4H7Uj4H&name=pdf) 98 | 99 | **LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS.** [Paper](https://openreview.net/attachment?id=6AeIDnrTN2&name=pdf) 100 | 101 | **Diversify, Contextualize, and Adapt: Efficient Entropy Modeling for Neural Image Codec.** [Paper](https://arxiv.org/pdf/2411.05832) 102 | 103 | **Causal Context Adjustment Loss for Learned Image Compression.** [Paper](https://arxiv.org/pdf/2410.04847); [Code](https://github.com/LabShuHangGU/CCA) 104 | 105 | **COSMIC: Compress Satellite Images Efficiently via Diffusion Compensation.** [Paper](https://arxiv.org/pdf/2410.01698) 106 | 107 | 108 | ## ACMMM 2024 109 | **Rate-aware Compression for NeRF-based Volumetric Video.** [Paper](https://arxiv.org/pdf/2411.05322) 110 | 111 | **Task-Oriented Multi-Bitstream Optimization for Image Compression and Transmission via Optimal Transport.** [Paper](https://openreview.net/pdf?id=wOx1VBzF8k) 112 | 113 | **Group-aware Parameter-efficient Updating for Content-Adaptive Neural Video Compression.** [Paper](https://openreview.net/attachment?id=KOIoLNLTAW&name=pdf) 114 | 115 | **Spatial-Temporal Context Model for Remote Sensing Imagery Compression.** [Paper](https://openreview.net/attachment?id=YTNN0mOPQN&name=pdf) 116 | 117 | **QS-NeRV: Real-Time Quality-Scalable Decoding with Neural Representation for Videos.** [Paper](https://openreview.net/attachment?id=vJbyT9bYgf&name=pdf) 118 | 119 | **HybridFlow: Infusing Continuity into Masked Codebook for Extreme Low-Bitrate Image Compression.** [Paper](https://openreview.net/attachment?id=jwuX7LktIH&name=pdf) 120 | 121 | **Consistency Guided Diffusion Model with Neural Syntax for Perceptual Image Compression.** [Paper](https://openreview.net/pdf?id=nSUMQhITdd) 122 | 123 | 124 | ## ECCV 2024 125 | **SNeRV: Spectra-preserving Neural Representation for Video.** [Paper](https://arxiv.org/pdf/2501.01681) 126 | 127 | **Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semantics.** [Paper](https://arxiv.org/abs/2408.02672) 128 | 129 | **Neural Graphics Texture Compression Supporting Random Acces.** [Paper](https://arxiv.org/abs/2407.00021) 130 | 131 | **MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation.** [Paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/4927_ECCV_2024_paper.php) 132 | 133 | **Lossy Image Compression with Foundation Diffusion Models.** [Paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/7844_ECCV_2024_paper.php) 134 | 135 | **Long-term Temporal Context Gathering for Neural Video Compression.** [Paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/8346_ECCV_2024_paper.php) 136 | 137 | **Free-VSC: Free Semantics from Visual Foundation Models for Unsupervised Video Semantic Compression.** [Paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/6543_ECCV_2024_paper.php) 138 | 139 | **Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinement.** [Paper](https://arxiv.org/abs/2408.02966) 140 | 141 | **A Unified Image Compression Method for Human Perception and Multiple Vision Tasks.** [Paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/9009_ECCV_2024_paper.php) 142 | 143 | **BaSIC: BayesNet Structure Learning for Computational Scalable Neural Image Compression.** [Paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/3640_ECCV_2024_paper.php); [Code](https://github.com/worldlife123/cbench_BaSIC) 144 | 145 | **Learned Rate Control for Frame-Level Adaptive Neural Video Compression via Dynamic Neural Network.** [Paper](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/11394.pdf) 146 | 147 | **Fast Encoding and Decoding for Implicit Video Representation.** [Paper](https://arxiv.org/pdf/2409.19429) 148 | 149 | **GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting.** [Paper](https://arxiv.org/pdf/2403.08551); [Code 150 | ](https://github.com/xinjie-q/gaussianimage) 151 | 152 | **Learned HDR Image Compression for Perceptually Optimal Storage and Display.** [Paper](https://arxiv.org/pdf/2407.13179); [Code](https://github.com/cpb68/EPIC-HDR) 153 | 154 | **Region Adaptive Transform with Segmentation Prior for Image Compression.** [Paper](https://arxiv.org/pdf/2403.00628); [Code](https://github.com/GityuxiLiu/SegPIC-for-Image-Compression) 155 | 156 | **WeConvene: Learned Image Compression with Wavelet-Domain Convolution and Entropy Model.** [Paper](https://arxiv.org/pdf/2407.09983); [Code](https://github.com/fengyurenpingsheng/WeConvene) 157 | 158 | **Rate-Distortion-Cognition Controllable Versatile Neural Image Compression.** [Paper](https://arxiv.org/pdf/2407.11700) 159 | 160 | **EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentation.** [Paper](https://arxiv.org/pdf/2309.03244) 161 | 162 | **Image Compression for Machine and Human Vision With Spatial-Frequency Adaptation.** [Paper](https://arxiv.org/pdf/2407.09853); [Code 163 | ](https://github.com/qingshi9974/eccv2024-adpaticmh) 164 | 165 | **HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression.** [Paper](https://arxiv.org/abs/2403.14530); [Code](https://github.com/YihangChen-ee/HAC) 166 | 167 | **Bidirectional Stereo Image Compression with Cross-Dimensional Entropy Model.** [Paper](https://arxiv.org/pdf/2407.10632) 168 | 169 | 170 | ## ICML 2024 171 | 172 | **Compress Clean Signal from Noisy Raw Image: A Self-Supervised Approach.** [Paper](https://openreview.net/attachment?id=5sgkNtexs2&name=pdf); [Code](https://github.com/lizhihao6/Cleans) 173 | 174 | **Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End Decoder.** [Paper](https://openreview.net/attachment?id=1WWpIEFdlk&name=pdf) 175 | 176 | **Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity.** [Paper](https://openreview.net/attachment?id=u8TZ9gm4im&name=pdf); [Code](https://github.com/effl-lab/taco) 177 | 178 | **EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens.** [Paper](https://openreview.net/attachment?id=nn5OPHom8t&name=pdf) 179 | 180 | 181 | 182 | ## CVPR 2024 183 | 184 | **DS-NeRV: Implicit Neural Video Representation with Decomposed Static and Dynamic Codes.** [Paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Yan_DS-NeRV_Implicit_Neural_Video_Representation_with_Decomposed_Static_and_Dynamic_CVPR_2024_paper.pdf) 185 | 186 | **JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficients.** [Paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Han_JDEC_JPEG_Decoding_via_Enhanced_Continuous_Cosine_Coefficients_CVPR_2024_paper.pdf) 187 | 188 | **Combining Frame and GOP Embeddings for Neural Video Representation.** [Paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Saethre_Combining_Frame_and_GOP_Embeddings_for_Neural_Video_Representation_CVPR_2024_paper.pdf) 189 | 190 | **C3: High-performance and Low-complexity Neural Compression from A Single Image or Video.** [Paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Kim_C3_High-Performance_and_Low-Complexity_Neural_Compression_from_a_Single_Image_CVPR_2024_paper.pdf) 191 | 192 | **Generative Latent Coding for Ultra-Low Bitrate Image Compression.** [Paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Jia_Generative_Latent_Coding_for_Ultra-Low_Bitrate_Image_Compression_CVPR_2024_paper.pdf) 193 | 194 | **Laplacian-guided Entropy Model in Neural Codec with Blur-dissipated Synthesis.** [Paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Khoshkhahtinat_Laplacian-guided_Entropy_Model_in_Neural_Codec_with_Blur-dissipated_Synthesis_CVPR_2024_paper.pdf) 195 | 196 | **Learned Lossless Image Compression based on Bit Plane Slicing.** [Paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Zhang_Learned_Lossless_Image_Compression_based_on_Bit_Plane_Slicing_CVPR_2024_paper.pdf) 197 | 198 | **Towards Backward-Compatible Continual Learning of Image Compression.** [Paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Duan_Towards_Backward-Compatible_Continual_Learning_of_Image_Compression_CVPR_2024_paper.pdf) 199 | 200 | **Enhancing Quality of Compressed Images by Mitigating Enhancement Bias Towards Compression Domain.** [Paper 201 | ](https://openaccess.thecvf.com/content/CVPR2024/papers/Xing_Enhancing_Quality_of_Compressed_Images_by_Mitigating_Enhancement_Bias_Towards_CVPR_2024_paper.pdf) 202 | 203 | **Boosting Neural Representations for Videos with a Conditional Decoder.** [Paper](https://arxiv.org/pdf/2402.18152.pdf); [Code 204 | ](https://github.com/Xinjie-Q/Boosting-NeRV) 205 | 206 | **Neural Video Compression with Feature Modulation.** [Paper](https://arxiv.org/pdf/2402.17414.pdf) 207 | 208 | **Task-Aware Encoder Control for Deep Video Compression.** [Paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Ge_Task-Aware_Encoder_Control_for_Deep_Video_Compression_CVPR_2024_paper.pdf) 209 | 210 | **NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation.** [Paper](https://openaccess.thecvf.com/content/CVPR2024/papers/Li_NeRFCodec_Neural_Feature_Compression_Meets_Neural_Radiance_Fields_for_Memory-Efficient_CVPR_2024_paper.pdf) 211 | 212 | 213 | ## ICLR 2024 214 | 215 | **Frequency-Aware Transformer for Learned Image Compression.** [Paper](https://openreview.net/pdf?id=HKGQDDTuvZ); [Code](https://github.com/qingshi9974/ICLR2024-Frequency-aware-Transformer-for-Learned-Image-Compression) 216 | 217 | **Idempotence and Perceptual Image Compression.** [Paper](https://openreview.net/pdf?id=Cy5v64DqEF); [Code](https://github.com/tongdaxu/Idempotence-and-Perceptual-Image-Compression) 218 | 219 | **Towards Image Compression with Perfect Realism At Ultra-Low Bitrates.** [Paper](https://openreview.net/attachment?id=ktdETU9JBg&name=pdf) 220 | 221 | **Neural Rate Control for Learned Video Compression.** [Paper](https://openreview.net/pdf?id=42lcaojZug) 222 | 223 | **Finite-State Autoregressive Entropy Coding for Efficient Learned Lossless Compression.** [Paper](https://openreview.net/attachment?id=D5mJSNtUtv&name=pdf) 224 | 225 | 226 | ## ICLR 2023 227 | 228 | **EVC: Towards Real-Time Neural Image Compression with Mask Decay.** [Paper](https://openreview.net/pdf?id=XUxad2Gj40n) 229 | 230 | **MIMT: Masked Image Modeling Transformer for Video Compression.** [Paper](https://openreview.net/pdf?id=j9m-mVnndbm) 231 | 232 | 233 | ## ICML 2023 234 | 235 | **Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models.** [Paper](https://openreview.net/attachment?id=iUspLfxpWC&name=pdf) 236 | 237 | **Modality-Agnostic Variational Compression of Implicit Neural Representations.** [Paper](https://openreview.net/pdf?id=bBXCCSoVQZ) 238 | 239 | **Is Overfitting Necessary for Implicit Video Representation?** [Paper](https://openreview.net/pdf?id=JuNIuHLm9y) 240 | 241 | 242 | ## AAAI 2023 243 | 244 | **Learned Distributed Image Compression with Multi-Scale Patch Matching in Feature Domain.** [Paper](https://ojs.aaai.org/index.php/AAAI/article/view/25551) 245 | 246 | **Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling.** [Paper](https://arxiv.org/pdf/2303.02353.pdf) 247 | 248 | **Multi-Modality Deep Network for Extreme Learned Image Compression.** [Paper](https://ojs.aaai.org/index.php/AAAI/article/view/25184) 249 | 250 | 251 | ## NeurIPS 2023 252 | 253 | **Neural Image Compression: Generalization, Robustness, and Spectral Biases.** [Paper](https://arxiv.org/pdf/2307.08657.pdf) 254 | 255 | **Compression with Bayesian Implicit Neural Representations.** [Paper](https://arxiv.org/pdf/2305.19185.pdf) 256 | 257 | **Towards Efficient Image Compression Without Autoregressive Models.** [Paper](https://openreview.net/pdf?id=1ihGy9vAIg) 258 | 259 | **Lossy Image Compression with Conditional Diffusion Models.** [Paper](https://arxiv.org/pdf/2209.06950v5.pdf) 260 | 261 | **Task-aware Distributed Source Coding Under Dynamic Bandwidth.** [Paper](https://openreview.net/pdf?id=1A4ZqTmnye) 262 | 263 | **On the Choice of Perception Loss Function for Learned Video Compression.** [Paper](https://openreview.net/pdf?id=kLIieSS2P3) 264 | 265 | **HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation.** [Paper](https://openreview.net/pdf?id=CpoS56pYnU) 266 | 267 | **Compact Neural Volumetric Video Representations with Dynamic Codebooks.** [Paper](https://openreview.net/pdf?id=xTgM7XLN9P) 268 | 269 | 270 | ## ICCV 2023 271 | 272 | **Computationally-Efficient Neural Image Compression with Shallow Decoders.** [Paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Yang_Computationally-Efficient_Neural_Image_Compression_with_Shallow_Decoders_ICCV_2023_paper.pdf) 273 | 274 | **SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representations.** [Paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Girish_SHACIRA_Scalable_HAsh-grid_Compression_for_Implicit_Neural_Representations_ICCV_2023_paper.pdf) 275 | 276 | **COMPASS: High-Efficiency Deep Image Compression with Arbitrary-scale Spatial Scalability.** [Paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Park_COMPASS_High-Efficiency_Deep_Image_Compression_with_Arbitrary-scale_Spatial_Scalability_ICCV_2023_paper.pdf) 277 | 278 | **Dec-Adapter: Exploring Efficient Decoder-Side Adapter for Bridging Screen Content and Natural Image Compression.** [Paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Shen_Dec-Adapter_Exploring_Efficient_Decoder-Side_Adapter_for_Bridging_Screen_Content_and_ICCV_2023_paper.pdf) 279 | 280 | **Semantically Structured Image Compression via Irregular Group-Based Decoupling.** [Paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Feng_Semantically_Structured_Image_Compression_via_Irregular_Group-Based_Decoupling_ICCV_2023_paper.pdf) 281 | 282 | **TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perception.** [Paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_TransTIC_Transferring_Transformer-based_Image_Compression_from_Human_Perception_to_Machine_ICCV_2023_paper.pdf) 283 | 284 | **RFD-ECNet: Extreme Underwater Image Compression with Reference to Feature Dictionary.** [Paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Li_RFD-ECNet_Extreme_Underwater_Image_Compression_with_Reference_to_Feature_Dictionary_ICCV_2023_paper.pdf) 285 | 286 | **AdaNIC: Towards Practical Neural Image Compression via Dynamic Transform Routing.** [Paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Tao_AdaNIC_Towards_Practical_Neural_Image_Compression_via_Dynamic_Transform_Routing_ICCV_2023_paper.pdf) 287 | 288 | **Non-Semantics Suppressed Mask Learning for Unsupervised Video Semantic Compression.** [Paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Tian_Non-Semantics_Suppressed_Mask_Learning_for_Unsupervised_Video_Semantic_Compression_ICCV_2023_paper.pdf) 289 | 290 | **Scene Matters: Model-based Deep Video Compression.** [Paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Tang_Scene_Matters_Model-based_Deep_Video_Compression_ICCV_2023_paper.pdf) 291 | 292 | 293 | ## CVPR 2023 294 | 295 | **Learned Image Compression With Mixed Transformer-CNN Architectures.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Learned_Image_Compression_With_Mixed_Transformer-CNN_Architectures_CVPR_2023_paper.pdf); [Code](https://github.com/jmliu206/LIC_TCM) 296 | 297 | **Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Tan_Backdoor_Attacks_Against_Deep_Image_Compression_via_Adaptive_Frequency_Trigger_CVPR_2023_paper.pdf) 298 | 299 | **TINC: Tree-structured Implicit Neural Compression.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_TINC_Tree-Structured_Implicit_Neural_Compression_CVPR_2023_paper.pdf) 300 | 301 | **Context-Based Trit-Plane Coding for Progressive Image Compression.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Jeon_Context-Based_Trit-Plane_Coding_for_Progressive_Image_Compression_CVPR_2023_paper.pdf) 302 | 303 | **LVQAC: Lattice Vector Quantization Coupled With Spatially Adaptive Companding for Efficient Learned Image Compression.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_LVQAC_Lattice_Vector_Quantization_Coupled_With_Spatially_Adaptive_Companding_for_CVPR_2023_paper.pdf) 304 | 305 | **Multi-Realism Image Compression With a Conditional Generator.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Agustsson_Multi-Realism_Image_Compression_With_a_Conditional_Generator_CVPR_2023_paper.pdf); [Code](https://github.com/Nikolai10/MRIC?tab=readme-ov-file) 306 | 307 | **AccelIR: Task-aware Image Compression for Accelerating Neural Restoration.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Ye_AccelIR_Task-Aware_Image_Compression_for_Accelerating_Neural_Restoration_CVPR_2023_paper.pdf) 308 | 309 | **Real-Time 6K Image Rescaling With Rate-Distortion Optimization.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Qi_Real-Time_6K_Image_Rescaling_With_Rate-Distortion_Optimization_CVPR_2023_paper.pdf) 310 | 311 | **Complexity-Guided Slimmable Decoder for Efficient Deep Video Compression.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Hu_Complexity-Guided_Slimmable_Decoder_for_Efficient_Deep_Video_Compression_CVPR_2023_paper.pdf) 312 | 313 | **Video Compression With Entropy-Constrained Neural Representations.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Gomes_Video_Compression_With_Entropy-Constrained_Neural_Representations_CVPR_2023_paper.pdf) 314 | 315 | **Neural Video Compression with Diverse Contexts.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Neural_Video_Compression_With_Diverse_Contexts_CVPR_2023_paper.pdf) 316 | 317 | **Motion Information Propagation for Neural Video Compression.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Qi_Motion_Information_Propagation_for_Neural_Video_Compression_CVPR_2023_paper.pdf) 318 | 319 | **MMVC: Learned Multi-Mode Video Compression With Block-Based Prediction Mode Selection and Density-Adaptive Entropy Coding.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_MMVC_Learned_Multi-Mode_Video_Compression_With_Block-Based_Prediction_Mode_Selection_CVPR_2023_paper.pdf) 320 | 321 | **DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Zhao_DNeRV_Modeling_Inherent_Dynamics_via_Difference_Neural_Representation_for_Videos_CVPR_2023_paper.pdf) 322 | 323 | **HNeRV: A Hybrid Neural Representation for Videos.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_HNeRV_A_Hybrid_Neural_Representation_for_Videos_CVPR_2023_paper.pdf); [Code](https://github.com/haochen-rye/HNeRV) 324 | 325 | **Hierarchical B-frame Video Coding Using Two-Layer CANF without Motion Coding.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Alexandre_Hierarchical_B-Frame_Video_Coding_Using_Two-Layer_CANF_Without_Motion_Coding_CVPR_2023_paper.pdf) 326 | 327 | **Towards Scalable Neural Representation for Diverse Videos.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/He_Towards_Scalable_Neural_Representation_for_Diverse_Videos_CVPR_2023_paper.pdf) 328 | 329 | **NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modeling.** [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Maiya_NIRVANA_Neural_Implicit_Representations_of_Videos_With_Adaptive_Networks_and_CVPR_2023_paper.pdf) 330 | 331 | 332 | ## ACMMM 2023 333 | 334 | **Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approach.** [Paper](https://dl.acm.org/doi/pdf/10.1145/3581783.3611851) 335 | 336 | **MLIC: Multi-Reference Entropy Model for Learned Image Compression.** [Paper](https://dl.acm.org/doi/pdf/10.1145/3581783.3611694); [Code](https://github.com/JiangWeibeta/MLIC) 337 | 338 | 339 | ## IEEE TPAMI 340 | **Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior. 2024.** [Paper](https://arxiv.org/pdf/2412.01646) 341 | 342 | **Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression. 2024.** [Paper](https://ieeexplore.ieee.org/document/10378746) 343 | 344 | **I2C: Invertible Continuous Codec for High-Fidelity Variable-Rate Image Compression. 2024.** [Paper](https://ieeexplore.ieee.org/document/10411123) 345 | 346 | **Insights from Generative Modeling for Neural Video Compression. 2023.** [Paper](https://arxiv.org/pdf/2107.13136.pdf) 347 | 348 | 349 | ## IEEE TCSVT 350 | **Rethinking the Functionality of Latent Representation: A Logarithmic Rate-Distortion Model for Learned Image Compression.** [Paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11016813) 351 | 352 | **Sparse Point Clouds Assisted Learned Image Compression. 2024.** [Paper](https://arxiv.org/pdf/2412.15752) 353 | 354 | **Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior. 2024.** [Paper](https://arxiv.org/pdf/2404.18820); [code](https://github.com/huai-chang/DiffEIC) 355 | 356 | **FDNet: Frequency Decomposition Network for Learned Image Compression. 2024.** [Paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10559830) 357 | 358 | **Conditional Residual Coding: A Remedy for Bottleneck Problems in Conditional Inter Frame Coding. 2024.** [Paper](https://ieeexplore.ieee.org/document/10416172) 359 | 360 | **Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compression. 2024.** [Paper](https://arxiv.org/pdf/2401.15864.pdf) 361 | 362 | **Exploring Resolution Fields for Scalable Image Compression with Uncertainty Guidance. 2023.** [Paper](https://arxiv.org/pdf/2306.08941.pdf) 363 | 364 | **Extremely Low Bit-rate Image Compression via Invertible Image Generation. 2023.** [Paper](https://ieeexplore.ieee.org/abstract/document/10256132) 365 | 366 | **DMVC: Decomposed Motion Modeling for Learned Video Compression. 2023.** [Paper](https://ieeexplore.ieee.org/abstract/document/10003249) 367 | 368 | 369 | ## IEEE TIP 370 | **MISC: Ultra-Low Bitrate Image Semantic Compression Driven by Large Multimodal Model. 2025.**[Paper](https://ieeexplore.ieee.org/abstract/document/10816592?casa_token=2xA-RPc6xpsAAAAA:dI9bmo3pCy7g_zPVRA_0Ww5XM0GkXE-tZB617OdkIr9191zOK9e3qQKcm_xYO52rX3lmHTbl); [Code](https://github.com/lcysyzxdxc/MISC) 371 | 372 | **Linearly transformed color guide for low-bitrate diffusion based image compression. 2024.** [Paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10818510) 373 | 374 | **Exploiting Latent Properties to Optimize Neural Codecs.** [Paper](https://arxiv.org/pdf/2501.01231) 375 | 376 | **Exploring Long- and Short-Range Temporal Information for Learned Video Compression. 2024.** [Paper](https://ieeexplore.ieee.org/abstract/document/10388053) 377 | 378 | **Learned Video Compression With Efficient Temporal Context Learning. 2023** [Paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10129217) 379 | 380 | **Scalable Face Image Coding via StyleGAN Prior: Toward Compression for Human-Machine Collaborative Vision. 2023.** [Paper](https://arxiv.org/pdf/2312.15622.pdf) 381 | 382 | **Learned Image Compression With Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules. 2023.** [Paper](https://ieeexplore.ieee.org/abstract/document/10091784) 383 | 384 | **Learning Cross-Scale Weighted Prediction for Efficient Neural Video Compression. 2023.** [Paper](https://ieeexplore.ieee.org/abstract/document/10159648) 385 | 386 | 387 | ## IEEE TMM 388 | 389 | **Uncertainty-Aware Deep Video Compression with Ensembles. 2024.** [Paper](https://arxiv.org/pdf/2403.19158.pdf) 390 | 391 | 392 | ## Other 393 | **Semantics-Guided Generative Image Compression. ICIP 2025.** [Paper](https://arxiv.org/pdf/2505.24015) 394 | 395 | **2025.06.03. Fourier-Modulated Implicit Neural Representation for Multispectral Satellite Image Compression.** [Paper](https://arxiv.org/pdf/2506.01234) 396 | 397 | **2025.05.30. Towards Facial Image Compression with Consistency Preserving Diffusion Prior.** [Paper](https://arxiv.org/pdf/2505.05870?) 398 | 399 | **2025.05.30. High Quality Underwater Image Compression with Adaptive Correction and Codebook-based Augmentation.** [Paper](https://arxiv.org/pdf/2505.09986?) 400 | 401 | **2025.05.30. 3DGS Compression with Sparsity-guided Hierarchical Transform Coding.** [Paper](https://arxiv.org/pdf/2505.22908) 402 | 403 | **2025.05.28.Generative Image Compression by Estimating Gradients of the Rate-variable Feature Distribution.** [Paper](https://arxiv.org/pdf/2505.20984) Shuhang Gu 404 | 405 | **2025.05.23. OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates.** [Paper](https://arxiv.org/pdf/2505.16091) Yulun Zhang 406 | 407 | **2025.05.23. Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression.** [Paper](https://arxiv.org/pdf/2505.16177) Yan Lu 408 | 409 | **2025.05.23. DualComp: End-to-End Learning of a Unified Dual-Modality Lossless Compressor.** [Paper](https://arxiv.org/pdf/2505.16256) 410 | 411 | **2025.05.23. One-Step Diffusion-Based Image Compression with Semantic Distillation.** [Paper](https://arxiv.org/pdf/2505.16687) Yan Lu 412 | 413 | **2025.05.16. High Quality Underwater Image Compression with Adaptive Correction and Codebook-based Augmentation.** [Paper](https://arxiv.org/pdf/2505.09986) 414 | 415 | **2025.05.15. Neural Video Compression using 2D Gaussian Splatting.** [Paper](https://arxiv.org/pdf/2505.09324) 416 | 417 | **2025.05.15. BiECVC: Gated Diversification of Bidirectional Contexts for Learned Video Compression.** [Paper](https://arxiv.org/pdf/2505.09193) 418 | 419 | **2025.04.08. 3DM-WeConvene: Learned Image Compression with 3D Multi-Level Wavelet-Domain Convolution and Entropy Model.** [Paper](https://arxiv.org/pdf/2504.04658) 420 | 421 | **2025.04.04. Image Coding for Machines via Feature-Preserving Rate-Distortion Optimization.** [Paper](https://arxiv.org/pdf/2504.02216) 422 | 423 | **L-LBVC: Long-Term Motion Estimation and Prediction for Learned Bi-Directional Video Compression. DCC 2025** [Paper](https://arxiv.org/pdf/2504.02560) 424 | 425 | **2025.03.30. Embedding Compression Distortion in Video Coding for Machines.** [Paper](https://arxiv.org/pdf/2503.21469) 426 | 427 | **2025.03.26. GIViC: Generative Implicit Video Compression.** [Paper](https://arxiv.org/pdf/2503.19604) 428 | 429 | **2025.03.22. Leveraging Diffusion Knowledge for Generative Image Compression with Fractal Frequency-Aware Band Learning.** [Paper](https://arxiv.org/pdf/2503.11321) 430 | 431 | **PerCoV2: Improved Ultra-Low Bit-Rate Perceptual Image Compression with Implicit Hierarchical Masked Image Modeling.** [Paper](https://arxiv.org/pdf/2503.09368) 432 | 433 | **Residual Learning and Filtering Networks for End-to-End Lossless Video Compression.** [Paper](https://arxiv.org/pdf/2503.08819) 434 | 435 | **Integrating Adaptive Sampling for Optimal Learned Video Compression.** [Paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10888457) 436 | 437 | **FEDS: Feature and Entropy-Based Distillation Strategy for Efficient Learned Image Compression.** [Paper](https://arxiv.org/pdf/2503.06399) 438 | 439 | **UAR-NVC: A Unified AutoRegressive Framework for Memory-Efficient Neural Video Compression.** [Paper](https://arxiv.org/abs/2503.02733) 440 | 441 | **DLF: Extreme Image Compression with Dual-generative Latent Fusion.** [Paper](https://arxiv.org/pdf/2503.01428) 442 | 443 | **Pleno-Generation: A Scalable Generative Face Video Compression Framework with Bandwidth Intelligence.** [Paper](https://arxiv.org/pdf/2502.17085) 444 | 445 | **Continuous Patch Stitching for Block-wise Image Compression.** [Paper](https://arxiv.org/pdf/2502.16795) 446 | 447 | **S2CFormer: Reorienting Learned Image Compression from Spatial Interaction to Channel Aggregation.** [Paper](https://arxiv.org/pdf/2502.00700) 448 | 449 | **HDCompression: Hybrid-Diffusion Image Compression for Ultra-Low Bitrates.** [Paper](https://arxiv.org/pdf/2502.07160) 450 | 451 | **Linear Attention Modeling for Learned Image Compression.** [Paper](https://arxiv.org/pdf/2502.05741) 452 | 453 | **CANeRV: Content Adaptive Neural Representation for Video Compression.** [Paper](https://arxiv.org/pdf/2502.06181) 454 | 455 | **CMamba: Learned Image Compression with State Space Models.** [Paper](https://arxiv.org/pdf/2502.04988) 456 | 457 | **Diffusion-based Perceptual Neural Video Compression with Temporal Diffusion Information Reuse.** [Paper](https://arxiv.org/pdf/2501.13528) 458 | 459 | **RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression.** [Paper](https://arxiv.org/pdf/2501.12216) 460 | 461 | **GaussianVideo: Efficient Video Representation Through 2D Gaussian Splatting.** [Paper](https://arxiv.org/pdf/2501.12060) 462 | 463 | **Locality-aware Gaussian Compression for Fast and High-quality Rendering.** [Paper](https://arxiv.org/pdf/2501.05757) 464 | 465 | **CoordFlow: Coordinate Flow for Pixel-wise Neural Video Representation.**[Paper](https://arxiv.org/pdf/2501.00975); [Code](https://github.com/Slivliver/CoordFlow) 466 | 467 | **Learned Compression for Compressed Learning. DCC2025.** [Paper](https://arxiv.org/pdf/2412.09405) 468 | 469 | **DeepFGS: Fine-Grained Scalable Coding for Learned Image Compression. DCC2024.** [Paper](https://arxiv.org/pdf/2412.00437) 470 | 471 | **Hybrid Local-Global Context Learning for Neural Video Compression. DCC2024.** [Paper](https://arxiv.org/pdf/2412.00446) 472 | 473 | **LMM-driven Semantic Image-Text Coding for Ultra Low-bitrate Learned Image Compression. VCIP2024.** [Paper](https://arxiv.org/pdf/2411.13033); [Code](https://github.com/tokkiwa/ImageTextCoding) 474 | 475 | **Efficient Progressive Image Compression with Variance-aware Masking. WACV2025.** [Paper](https://arxiv.org/abs/2411.10185) 476 | 477 | **Conditional Hallucinations for Image Compression.** [Paper](https://arxiv.org/abs/2410.19493) 478 | 479 | **Extreme Image Compression Using Fine-tuned VQGANs. DCC2024.** [Paper](https://ieeexplore.ieee.org/document/10533792); [Code](https://github.com/CUC-MIPG/VQGAN-Compression) 480 | --------------------------------------------------------------------------------