└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # A summary of image compression papers & code 2 | :heavy_check_mark: [Variable Rate Image Compression with Recurrent Neural Networks][[paper]](https://arxiv.org/abs/1511.06085)[code] 3 | 4 | :heavy_check_mark: [Full Resolution Image Compression with Recurrent Neural Networks][[paper]](http://openaccess.thecvf.com/content_cvpr_2017/papers/Toderici_Full_Resolution_Image_CVPR_2017_paper.pdf)[[code]](https://github.com/tensorflow/models/tree/master/research/compression) 5 | 6 | :heavy_check_mark: [Improved Lossy Image Compression with Priming and Spatially Adaptive Bit 7 | Rates for Recurrent Networks][[paper]](http://openaccess.thecvf.com/content_cvpr_2018/CameraReady/1904.pdf)[code] 8 | 9 | :heavy_check_mark: [Lossy Image Compression with Compressive Autoencoders][[paper]](https://arxiv.org/abs/1703.00395)[[code_version1]](https://github.com/zhiqiang-zhu/cae)[[code_version2]](https://github.com/alexandru-dinu/cae) 10 | 11 | :heavy_check_mark: [Real-Time Adaptive Image Compression][[paper]](https://arxiv.org/abs/1705.05823)[code] 12 | 13 | :heavy_check_mark: [Learning to Inpaint for Image Compression][[paper]](http://papers.nips.cc/paper/6724-learning-to-inpaint-for-image-compression.pdf)[code] 14 | 15 | :heavy_check_mark: [Conditional Probability Models for Deep Image Compression][[paper]](http://openaccess.thecvf.com/content_cvpr_2018/CameraReady/2172.pdf)[[code]](https://github.com/fab-jul/imgcomp-cvpr) 16 | 17 | :heavy_check_mark: [Generative Adversarial Networks for Extreme Learned Image Compression][[paper]](https://arxiv.org/abs/1804.02958)[[code]](https://github.com/Justin-Tan/generative-compression) 18 | 19 | :heavy_check_mark: [Learning Convolutional Networks for Content-weighted Image Compression][[paper]](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Learning_Convolutional_Networks_CVPR_2018_paper.pdf)[[code]](https://github.com/limuhit/ImageCompression) 20 | 21 | :heavy_check_mark: [End-to-end Optimized Image Compression][[paper]](https://arxiv.org/abs/1611.01704)[[code]](https://github.com/tensorflow/compression) 22 | 23 | :heavy_check_mark: [Towards Conceptual Compression][[paper]](http://papers.nips.cc/paper/6542-towards-conceptual-compression.pdf)[[code]](https://github.com/musyoku/convolutional-draw) 24 | 25 | :heavy_check_mark: [Guetzli: Perceptually Guided JPEG Encode][[paper]](https://arxiv.org/pdf/1703.04421.pdf)[[code]](https://github.com/zhiqiang-zhu/guetzli) 26 | 27 | :heavy_check_mark: [Soft-to-Hard Vector Quantization for End-to-End 28 | Learning Compressible Representations][[paper]](http://papers.nips.cc/paper/6714-soft-to-hard-vector-quantization-for-end-to-end-learning-compressible-representations.pdf)[code] 29 | 30 | :heavy_check_mark: [An End-to-End Compression Framework Based on Convolutional Neural Networks][[paper]](https://ieeexplore.ieee.org/document/7923746)[[code]](https://github.com/compression-framework/compression_framwork_for_tesing) 31 | 32 | :heavy_check_mark: [CAE-ADMM Implicit Bitrate Optimization via ADMM-based Pruning in Compressive Autoencoders 33 | ][[paper]](https://arxiv.org/abs/1901.07196)[[code]](https://github.com/JasonZHM/CAE-ADMM) 34 | 35 | :heavy_check_mark: [Learned Image Compression with Soft Bit-based Rate-Distortion Optimization][[paper]][code] 36 | 37 | :heavy_check_mark: [Extreme Image Compression via Multiscale Autoencoders With Generative Adversarial Optimization][[paper]][code] 38 | 39 | :heavy_check_mark: [Variational image compression with a scale hyperprior][[paper]][code] 40 | 41 | :heavy_check_mark: [DSSLIC: Deep Semantic Segmentation-based Layered Image Compression][[paper]](https://arxiv.org/pdf/1806.03348.pdf)[[code]](https://github.com/makbari7/DSSLIC) 42 | 43 | 44 | # Image super-resolution 45 | :heavy_check_mark: [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs][[paper]](https://arxiv.org/abs/1711.11585)[[code]](https://github.com/NVIDIA/pix2pixHD) 46 | 47 | :heavy_check_mark: [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network][[paper]](https://arxiv.org/abs/1609.04802)[[code_PyTorch]](https://github.com/goldhuang/SRGAN-PyTorch)[[code_TF]](https://github.com/brade31919/SRGAN-tensorflow) 48 | 49 | :heavy_check_mark: [Convolutional Sparse Coding for Image Super-resolution][[paper]](http://www4.comp.polyu.edu.hk/~cslzhang/paper/CSC_SR.pdf)[[code]](http://www4.comp.polyu.edu.hk/~cslzhang/papers.htm) 50 | 51 | :heavy_check_mark: [ESRGAN: Enhanced Super-Resolution 52 | Generative Adversarial Networks][[paper]](https://arxiv.org/pdf/1809.00219v2.pdf)[[code]](https://github.com/xinntao/ESRGAN) 53 | 54 | :heavy_check_mark: [Real-Time Single Image and Video Super-Resolution Using an Efficient 55 | Sub-Pixel Convolutional Neural Network][[paper]](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Shi_Real-Time_Single_Image_CVPR_2016_paper.pdf)[[code]](https://github.com/leftthomas/ESPCN) 56 | 57 | :heavy_check_mark: [Image Super-Resolution Using Deep Convolutional Networks][[paper]](https://arxiv.org/pdf/1501.00092.pdf)[[code]](http://mmlab.ie.cuhk.edu.hk/projects/SRCNN.html) 58 | --------------------------------------------------------------------------------