未完成
文献
| 论文简称 | 论文名称 | 文章地址 | 源码地址 |
|---|---|---|---|
| SRCNN | Image Super-Resolution Using Deep Convolutional Networks | https://arxiv.org/abs/1501.00092 | http://mmlab.ie.cuhk.edu.hk/projects/SRCNN/SRCNN_train.zip (caffe)， http://mmlab.ie.cuhk.edu.hk/projects/SRCNN/SRCNN_v1.zip (MATLAB), https://github.com/tegg89/SRCNN-Tensorflow (TensorFlow，非作者) |
| FSRCNN | Accelerating the Super-Resolution Convolutional Neural Network | https://arxiv.org/abs/1608.00367 | https://drive.google.com/open?id=0B7tU5Pj1dfCMWjhhaE1HR3dqcGs (caffe), https://drive.google.com/open?id=0B7tU5Pj1dfCMVktYZUN2aV8xVTQ (MATLAB) |
| VDSR | Accurate Image Super-Resolution Using Very Deep Convolutional Networks | https://arxiv.org/abs/1511.04587 | https://github.com/twtygqyy/pytorch-vdsr（PyTorch，非作者） |
| ESPCN | Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network | https://arxiv.org/abs/1609.05158 | https://github.com/leftthomas/ESPCN（PyTorch，非作者） |
| LapSRN | Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks | https://arxiv.org/abs/1710.01992 | https://github.com/phoenix104104/LapSRN (MATLAB), https://github.com/twtygqyy/pytorch-LapSRN （PyTorch，非作者） |
| EDSR | Enhanced Deep Residual Networks for Single Image Super-Resolution | https://arxiv.org/abs/1707.02921 | https://github.com/LimBee/NTIRE2017 (torch), https://github.com/thstkdgus35/EDSR-PyTorch (PyTorch) |
| RCAN | Image Super-Resolution Using Very Deep Residual Channel Attention Networks | https://arxiv.org/abs/1807.02758 | https://github.com/yulunzhang/RCAN (PyTorch) |
| SRGAN | Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network | https://arxiv.org/abs/1609.04802 | https://github.com/tensorlayer/srgan （TensorFlow，非作者）， https://github.com/leftthomas/SRGAN （PyTorch，非作者） |
| ESRGAN | ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks | https://arxiv.org/abs/1809.00219 | https://github.com/xinntao/ESRGAN (PyTorch), https://github.com/xinntao/BasicSR (PyTorch) |
| SFTGAN | Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform | https://arxiv.org/abs/1804.02815 | https://github.com/xinntao/SFTGAN (PyTorch), https://github.com/xinntao/BasicSR (PyTorch) |
| Meta-SR | Meta-SR: A Magnification-Arbitrary Network for Super-Resolution | https://arxiv.org/abs/1903.00875 | https://github.com/XuecaiHu/Meta-SR-Pytorch |
| DRN | Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution | https://arxiv.org/abs/2003.07018 | https://github.com/guoyongcs/DRN |
| CutBlur | Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy | https://arxiv.org/abs/2004.00448 | https://github.com/clovaai/cutblur |
| EDVR | EDVR: Video Restoration with Enhanced Deformable Convolutional Networks | https://arxiv.org/abs/1905.02716 | https://github.com/xinntao/EDVR (PyTorch), https://github.com/xinntao/BasicSR (PyTorch) |
常用数据
Set5，Set14，Urban100，BSD100，Sun-Hays 80（均为小数据集）：
https://github.com/jbhuang0604/SelfExSR
Flickr2K（20G）：
http://cv.snu.ac.kr/research/EDSR/Flickr2K.tar
DIV2K（8G+）
https://data.vision.ee.ethz.ch/cvl/DIV2K/