图像超分辨率重建顶会论文整理（项目地址，代码实现平台）（17-18年）

CVPR2017, CVPR2018, ECCV2018, ICCV2017

 

• Learning a Single Convolutional Super-Resolution Network for Multiple Degradations

https://github.com/cszn/SRMD

 (matlab)

 

• Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform

http://mmlab.ie.cuhk.edu.hk/projects/SFTGAN/

(pytorch)

 

• Deep Back-Projection Networks For Super-Resolution

https://www.toyota-ti.ac.jp/Lab/Denshi/iim/members/muhammad.haris/projects/DBPN.html

 (Pytorch / Caffe)

 

• Image Super-resolution via Dual-state Recurrent Neural Networks

https://github.com/weihan3/dsrn

(tensorflow)

 

• Fast and Accurate Single Image Super-Resolution via Information Distillation Network

https://github.com/Zheng222/IDN-Caffe

(matlab+caffe)

 

• "Zero-Shot" Super-Resolution using Deep Internal Learning (ZSSR)

https://github.com/assafshocher/ZSSR

(Pytorch)

 

• Residual Dense Network for Image Super-Resolution

https://github.com/yulunzhang/RDN

 (Pytorch)

 

• Image Super-Resolution via Deep Recursive Residual Network

https://github.com/tyshiwo/DRRN_CVPR17

 (caffe tensorflow pytorch)

 

• Deeply-Recursive Convolutional Network for Image Super-Resolution

(matlab)

 

• Accurate Image Super-Resolution Using Very Deep Convolutional Networks

(matlab)

 

• Image Super-Resolution Using Very Deep Residual Channel Attention Networks

https://github.com/yulunzhang/RCAN

(Pytorch)

 

• SRFeat: Single Image Super-Resolution with Feature Discrimination

https://github.com/HyeongseokSon1/SRFeat

(matlab + Pytorch)

 

• CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warping

https://github.com/htzheng/ECCV2018_CrossNet_RefSR

 (Pytorch)

 

• To learn image super-resolution, use a GAN to learn how to do image degradation first

https://github.com/jingyang2017/Face-and-Image-super-resolution

(Pytorch)

 

• Enhanced Deep Residual Networks for Single Image Super-Resolution

https://github.com/thstkdgus35/EDSR-PyTorch

 (Pytorch)

 

• Image Super-Resolution Using Very Deep Residual Channel Attention Networks

https://github.com/yulunzhang/RCAN

(Pytorch)

 

• Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network

https://github.com/nmhkahn/CARN-pytorch

(Pytorch)

 

• ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks

https://github.com/xinntao/ESRGAN

(Pytorch)