GitHub：超分辨率最全资料集锦
作者：ChaofWang | 编辑：Amusi
前言
本文将分享的内容是：超分辨率（Super Resolution，SR）最全资料合集，涵盖了SISR、VSR等。
一张图看懂超分辨率SR作用
注：文末附超分辨率SR微信交流群，欢迎加入学习
Awesome-Super-Resolution
项目作者：ChaofWang Star
数量：636 Commit
数量：120
https://github.com/ChaofWang/Awesome-Super-Resolution
该项目主要包含以下内容：
- 最佳论文库/项目列表
- 数据集
- 论文：非深度学习方法、深度学习方法（2014-2020）
- workshop论文
- 综述
其中每个部分介绍的都非常详细，比如一个论文，会相应介绍其论文链接和相应的开源代码。
最佳论文库
这里算是致敬！github上其实有很多不错的超分辨率SR合集项目，比如：
Single-Image-Super-Resolution
Super-Resolution.Benckmark
Video-Super-Resolution
VideoSuperResolution
Awesome Super-Resolution
Awesome-LF-Image-SR
Awesome-Stereo-Image-SR
AI-video-enhance
最佳项目库
不少顶会上的SR论文都是基于下面的优秀开源项目所开发的，
| repo | Framework |
|---|---|
| EDSR-PyTorch | PyTorch |
| Image-Super-Resolution | Keras |
| image-super-resolution | Keras |
| Super-Resolution-Zoo | MxNet |
| super-resolution | Keras |
| neural-enhance | Theano |
| srez | Tensorflow |
| waifu2x | Torch |
| BasicSR | PyTorch |
| super-resolution | PyTorch |
| VideoSuperResolution | Tensorflow |
| video-super-resolution | Pytorch |
| MMSR | PyTorch |
数据集
系统性整理了非常多的数据集，并都提供了下载链接，整理的很用心。比如Set14、BSD100和Urban100等。
| Name | Usage | Link | Comments |
|---|---|---|---|
| Set5 | Test | download | jbhuang0604 |
| SET14 | Test | download | jbhuang0604 |
| BSD100 | Test | download | jbhuang0604 |
| Urban100 | Test | download | jbhuang0604 |
| Manga109 | Test | website | |
| SunHay80 | Test | download | jbhuang0604 |
| BSD300 | Train/Val | download | |
| BSD500 | Train/Val | download | |
| 91-Image | Train | download | Yang |
| DIV2K2017 | Train/Val | website | NTIRE2017 |
| Flickr2K | Train | download | |
| Real SR | Train/Val | website | NTIRE2019 |
| Waterloo | Train | website | |
| VID4 | Test | download | 4 videos |
| MCL-V | Train | website | 12 videos |
| GOPRO | Train/Val | website | 33 videos, deblur |
| CelebA | Train | website | Human faces |
| Sintel | Train/Val | website | Optical flow |
| FlyingChairs | Train | website | Optical flow |
| Vimeo-90k | Train/Test | website | 90k HQ videos |
| SR-RAW | Train/Test | website | raw sensor image dataset |
| W2S | Train/Test | arxiv | A Joint Denoising and Super-Resolution Dataset |
| PIPAL | Test | ECCV 2020 | Perceptual Image Quality Assessment dataset |
论文：深度学习方法（2014-2020）
2014-2016
| Model | Published | Code | Keywords |
|---|---|---|---|
| SRCNN | ECCV14 | Keras | Kaiming |
| RAISR | arXiv | - | Google, Pixel 3 |
| ESPCN | CVPR16 | Keras | Real time/SISR/VideoSR |
| VDSR | CVPR16 | Matlab | Deep, Residual |
| DRCN | CVPR16 | Matlab | Recurrent |
2017
| Model | Published | Code | Keywords |
|---|---|---|---|
| DRRN | CVPR17 | Caffe, PyTorch | Recurrent |
| LapSRN | CVPR17 | Matlab | Huber loss |
| IRCNN | CVPR17 | Matlab | |
| EDSR | CVPR17 | PyTorch | NTIRE17 Champion |
| BTSRN | CVPR17 | - | NTIRE17 |
| SelNet | CVPR17 | - | NTIRE17 |
| TLSR | CVPR17 | - | NTIRE17 |
| SRGAN | CVPR17 | Tensorflow | 1st proposed GAN |
| VESPCN | CVPR17 | - | VideoSR |
| MemNet | ICCV17 | Caffe | |
| SRDenseNet | ICCV17 | -, PyTorch | Dense |
| SPMC | ICCV17 | Tensorflow | VideoSR |
| EnhanceNet | ICCV17 | TensorFlow | Perceptual Loss |
| PRSR | ICCV17 | TensorFlow | an extension of PixelCNN |
| AffGAN | ICLR17 | - |
2018
| Model | Published | Code | Keywords |
|---|---|---|---|
| MS-LapSRN | TPAMI18 | Matlab | Fast LapSRN |
| DCSCN | arXiv | Tensorflow | |
| IDN | CVPR18 | Caffe | Fast |
| DSRN | CVPR18 | TensorFlow | Dual state，Recurrent |
| RDN | CVPR18 | Torch | Deep, BI-BD-DN |
| SRMD | CVPR18 | Matlab | Denoise/Deblur/SR |
| xUnit | CVPR18 | PyTorch | Spatial Activation Function |
| DBPN | CVPR18 | PyTorch | NTIRE18 Champion |
| WDSR | CVPR18 | PyTorch，TensorFlow | NTIRE18 Champion |
| ProSRN | CVPR18 | PyTorch | NTIRE18 |
| ZSSR | CVPR18 | Tensorflow | Zero-shot |
| FRVSR | CVPR18 | VideoSR | |
| DUF | CVPR18 | Tensorflow | VideoSR |
| TDAN | arXiv | - | VideoSR，Deformable Align |
| SFTGAN | CVPR18 | PyTorch | |
| CARN | ECCV18 | PyTorch | Lightweight |
| RCAN | ECCV18 | PyTorch | Deep, BI-BD-DN |
| MSRN | ECCV18 | PyTorch | |
| SRFeat | ECCV18 | Tensorflow | GAN |
| TSRN | ECCV18 | Pytorch | |
| ESRGAN | ECCV18 | PyTorch | PRIM18 region 3 Champion |
| EPSR | ECCV18 | PyTorch | PRIM18 region 1 Champion |
| PESR | ECCV18 | PyTorch | ECCV18 workshop |
| FEQE | ECCV18 | Tensorflow | Fast |
| NLRN | NIPS18 | Tensorflow | Non-local, Recurrent |
| SRCliqueNet | NIPS18 | - | Wavelet |
| CBDNet | arXiv | Matlab | Blind-denoise |
| TecoGAN | arXiv | Tensorflow | VideoSR GAN |
2019
| Model | Published | Code | Keywords |
|---|---|---|---|
| RBPN | CVPR19 | PyTorch | VideoSR |
| SRFBN | CVPR19 | PyTorch | Feedback |
| AdaFM | CVPR19 | PyTorch | Adaptive Feature Modification Layers |
| MoreMNAS | arXiv | - | Lightweight，NAS |
| FALSR | arXiv | TensorFlow | Lightweight，NAS |
| Meta-SR | CVPR19 | PyTorch | Arbitrary Magnification |
| AWSRN | arXiv | PyTorch | Lightweight |
| OISR | CVPR19 | PyTorch | ODE-inspired Network |
| DPSR | CVPR19 | PyTorch | |
| DNI | CVPR19 | PyTorch | |
| MAANet | arXiv | Multi-view Aware Attention | |
| RNAN | ICLR19 | PyTorch | Residual Non-local Attention |
| FSTRN | CVPR19 | - | VideoSR, fast spatio-temporal residual block |
| MsDNN | arXiv | TensorFlow | NTIRE19 real SR 21th place |
| SAN | CVPR19 | Pytorch | Second-order Attention,cvpr19 oral |
| EDVR | CVPRW19 | Pytorch | Video, NTIRE19 video restoration and enhancement champions |
| Ensemble for VSR | CVPRW19 | - | VideoSR, NTIRE19 video SR 2nd place |
| TENet | arXiv | Pytorch | a Joint Solution for Demosaicking, Denoising and Super-Resolution |
| MCAN | arXiv | Pytorch | Matrix-in-matrix CAN, Lightweight |
| IKC&SFTMD | CVPR19 | - | Blind Super-Resolution |
| SRNTT | CVPR19 | TensorFlow | Neural Texture Transfer |
| RawSR | CVPR19 | TensorFlow | Real Scene Super-Resolution, Raw Images |
| resLF | CVPR19 | Light field | |
| CameraSR | CVPR19 | realistic image SR | |
| ORDSR | TIP | model | DCT domain SR |
| U-Net | CVPRW19 | NTIRE19 real SR 2nd place, U-Net,MixUp,Synthesis | |
| DRLN | arxiv | Densely Residual Laplacian Super-Resolution | |
| EDRN | CVPRW19 | Pytorch | NTIRE19 real SR 9th places |
| FC2N | arXiv | Fully Channel-Concatenated | |
| GMFN | BMVC2019 | Pytorch | Gated Multiple Feedback |
| CNN&TV-TV Minimization | BMVC2019 | TV-TV Minimization | |
| HRAN | arXiv | Hybrid Residual Attention Network | |
| PPON | arXiv | code | Progressive Perception-Oriented Network |
| SROBB | ICCV19 | Targeted Perceptual Loss | |
| RankSRGAN | ICCV19 | PyTorch | oral, rank-content loss |
| edge-informed | ICCVW19 | PyTorch | Edge-Informed Single Image Super-Resolution |
| s-LWSR | arxiv | Lightweight | |
| DNLN | arxiv | Video SR Deformable Non-local Network | |
| MGAN | arxiv | Multi-grained Attention Networks | |
| IMDN | ACM MM 2019 | PyTorch | AIM19 Champion |
| ESRN | arxiv | NAS | |
| PFNL | ICCV19 | Tensorflow | VideoSR oral,Non-Local Spatio-Temporal Correlations |
| EBRN | ICCV19 | Tensorflow | Embedded Block Residual Network |
| Deep SR-ITM | ICCV19 | matlab | SDR to HDR, 4K SR |
| feature SR | ICCV19 | Super-Resolution for Small Object Detection | |
| STFAN | ICCV19 | PyTorch | Video Deblurring |
| KMSR | ICCV19 | PyTorch | GAN for blur-kernel estimation |
| CFSNet | ICCV19 | PyTorch | Controllable Feature |
| FSRnet | ICCV19 | Multi-bin Trainable Linear Units | |
| SAM+VAM | ICCVW19 | ||
| SinGAN | ICCV19 | PyTorch | bestpaper, train from single image |
2020
| Model | Published | Code | Keywords |
|---|---|---|---|
| FISR | AAAI 2020 | TensorFlow | Video joint VFI-SR method,Multi-scale Temporal Loss |
| ADCSR | arxiv | ||
| SCN | AAAI 2020 | Scale-wise Convolution | |
| LSRGAN | arxiv | Latent Space Regularization for srgan | |
| Zooming Slow-Mo | CVPR 2020 | PyTorch | joint VFI and SR，one-stage， deformable ConvLSTM |
| MZSR | CVPR 2020 | Meta-Transfer Learning, Zero-Shot | |
| VESR-Net | arxiv | Youku Video Enhancement and Super-Resolution Challenge Champion | |
| blindvsr | arxiv | PyTorch | Motion blur estimation |
| HNAS-SR | arxiv | PyTorch | Hierarchical Neural Architecture Search, Lightweight |
| DRN | CVPR 2020 | PyTorch | Dual Regression, SISR STOA |
| SFM | arxiv | PyTorch | Stochastic Frequency Masking, Improve method |
| EventSR | CVPR 2020 | split three phases | |
| USRNet | CVPR 2020 | PyTorch | |
| PULSE | CVPR 2020 | Self-Supervised | |
| SPSR | CVPR 2020 | Code | Gradient Guidance, GAN |
| DASR | arxiv | Code | Real-World Image Super-Resolution, Unsupervised SuperResolution, Domain Adaptation. |
| STVUN | arxiv | PyTorch | Video Super-Resolution, Video Frame Interpolation, Joint space-time upsampling |
| AdaDSR | arxiv | PyTorch | Adaptive Inference |
| Scale-Arbitrary SR | arxiv | Code | Scale-Arbitrary Super-Resolution, Knowledge Transfer |
| DeepSEE | arxiv | Code | Extreme super-resolution,32× magnification |
| CutBlur | CVPR 2020 | PyTorch | SR Data Augmentation |
| UDVD | CVPR 2020 | Unified Dynamic Convolutional，SISR and denoise | |
| DIN | IJCAI-PRICAI 2020 | SISR，asymmetric co-attention | |
| PANet | arxiv | PyTorch | Pyramid Attention |
| SRResCGAN | arxiv | PyTorch | |
| ISRN | arxiv | iterative optimization, feature normalization. | |
| RFB-ESRGAN | CVPR 2020 | NTIRE 2020 Perceptual Extreme Super-Resolution Challenge winner | |
| PHYSICS_SR | AAAI 2020 | PyTorch | |
| CSNLN | CVPR 2020 | PyTorch | Cross-Scale Non-Local Attention,Exhaustive Self-Exemplars Mining, Similar to PANet |
| TTSR | CVPR 2020 | PyTorch | Texture Transformer |
| NSR | arxiv | PyTorch | Neural Sparse Representation |
| RFANet | CVPR 2020 | state-of-the-art SISR | |
| Correction filter | CVPR 2020 | Enhance SISR model generalization | |
| Unpaired SR | CVPR 2020 | Unpaired Image Super-Resolution | |
| STARnet | CVPR 2020 | Space-Time-Aware multi-Resolution | |
| SSSR | CVPR 2020 | code | SISR for Semantic Segmentation and Human pose estimation |
| VSR_TGA | CVPR 2020 | code | Temporal Group Attention, Fast Spatial Alignment |
| SSEN | CVPR 2020 | Similarity-Aware Deformable Convolution |
| SMSR | arxiv | | Sparse Masks, Efficient SISR
| LF-InterNet | ECCV 2020 | PyTorch | Spatial-Angular Interaction, Light Field Image SR |
| Invertible-Image-Rescaling | ECCV 2020 | Code | ECCV oral |
| IGNN | arxiv | Code | GNN, SISR |
| MIRNet | ECCV 2020 | PyTorch | multi-scale residual block |
| SFM | ECCV 2020 | PyTorch | stochastic frequency mask |
| TCSVT | arxiv | TensorFlow | LightWeight modules |
| PISR | ECCV 2020 | PyTorch | FSRCNN,distillation framework, HR privileged information |
| MuCAN | ECCV 2020 | | VideoSR, Temporal Multi-Correspondence Aggregation |
| DGP | ECCV 2020 |PyTorch | ECCV oral, GAN, Image Restoration and Manipulation, |
| RSDN| ECCV 2020 |Code | VideoSR, Recurrent Neural Network, TwoStream Block|
| CDC| ECCV 2020 |PyTorch | Diverse Real-world SR dataset, Component Divide-and-Conquer model, GradientWeighted loss|
| MS3-Conv| arxiv | | Multi-Scale cross-Scale Share-weights convolution |
| OverNet| arxiv | | Lightweight, Overscaling Module, multi-scale loss, Arbitrary Scale Factors |
| RRN| BMVC20 | code | VideoSR, Recurrent Residual Network, temporal modeling method |
| NAS-DIP| ECCV 2020 | | NAS|
| SRFlow| ECCV 2020 |code | Spotlight, Normalizing Flow|
| LatticeNet| ECCV 2020 | |Lattice Block, LatticeNet, Lightweight, Attention|
| BSRN| ECCV 2020 | |Model Quantization, Binary Neural Network, Bit-Accumulation Mechanism|
| VarSR| ECCV 2020 | |Variational Super-Resolution, very low resolution |
| HAN| ECCV 2020 | |SISR, holistic attention network, channel-spatial attention module |
| DeepTemporalSR| ECCV 2020 | |Temporal Super-Resolution |
| DGDML-SR| ECCV 2020 | |Zero-Shot, Depth Guided Internal Degradation Learning |
|MLSR| ECCV 2020 | |Meta-learning, Patch recurrence |
|PlugNet| ECCV 2020 | |Scene Text Recognition, Feature Squeeze Module |
|TextZoom| ECCV 2020 |code |Scene Text Recognition |
|TPSR| ECCV 2020 | |NAS,Tiny Perceptual SR |
|CUCaNet| ECCV 2020 | PyTorch |Coupled unmixing, cross-attention,hyperspectral super-resolution, multispectral, unsupervised |
|MAFFSRN| ECCVW 2020 | |Multi-Attentive Feature Fusion, Ultra Lightweight |
|SRResCycGAN| ECCVW 2020 | PyTorch |RealSR, CycGAN |
|A-CubeNet| arxiv | |SISR, lightweight|
|MoG-DUN| arxiv | |SISR |
|Understanding Deformable Alignment| arxiv | | VideoSR, EDVR, offset-fidelity loss |
|AdderSR| arxiv | | SISR, adder neural networks, Energy Efficient |
|RFDN| arxiv | | SISR, Lightweight, IMDN, AIM20 WINNER |
|Tarsier| arxiv | | improve NESRGAN+,injected noise, Diagonal CMA optimize |
|DeFiAN| arxiv | PyTorch |SISR, detail-fidelity attention, Hessian filtering |
|ASDN| arxiv | | Arbitrary Scale SR |
|DAN| NeurIPS 2020 |PyTorch | Unfolding the Alternating Optimization |
|DKC| ECCVW 2020 | | Deformable Kernel Convolutional, VSR |
|FAN| ECCVW 2020 | | Frequency aggregation network, RealSR |
|PAN| ECCVW 2020 |PyTorch | Lightweight, Pixel Attention |
|SCHN| arxiv | | Blind SR, Spatial Context Hallucination |
综述
[1] Wenming Yang, Xuechen Zhang, Yapeng Tian, Wei Wang, Jing-Hao Xue. Deep Learning for Single Image Super-Resolution: A Brief Review. arxiv, 2018. paper
[2]Saeed Anwar, Salman Khan, Nick Barnes. A Deep Journey into Super-resolution: A survey. arxiv, 2019.paper
[3]Wang, Z., Chen, J., & Hoi, S. C. (2019). Deep learning for image super-resolution: A survey. arXiv preprint arXiv:1902.06068.paper
[4]Hongying Liu and Zhubo Ruan and Peng Zhao and Fanhua Shang and Linlin Yang and Yuanyuan Liu. Video Super Resolution Based on Deep Learning: A comprehensive survey. arXiv preprint arXiv:2007.12928.[paper](
侃侃
本项目包含的超分辨率SR论文、开源项目相当多，十分推荐学习！
https://github.com/ChaofWang/Awesome-Super-Resolution
资料下载
在CVer公众号后台回复：超分辨率，即可下载访问最全的超分辨率SR论文、开源项目等资料。
