Awesome-Super-Resolution

Quick navigation

Awesome-Super-Resolution(in progress)

Collect some super-resolution related papers, data and repositories.

repositories

Awesome paper list:

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

Awesome repos:

repoFramework
EDSR-PyTorchPyTorch
Image-Super-ResolutionKeras
image-super-resolutionKeras
Super-Resolution-ZooMxNet
super-resolutionKeras
neural-enhanceTheano
srezTensorflow
waifu2xTorch
BasicSRPyTorch
super-resolutionPyTorch
VideoSuperResolutionTensorflow
video-super-resolutionPytorch
MMSRPyTorch

Datasets

Note this table is referenced from here.

NameUsageLinkComments
Set5Testdownloadjbhuang0604
SET14Testdownloadjbhuang0604
BSD100Testdownloadjbhuang0604
Urban100Testdownloadjbhuang0604
Manga109Testwebsite 
SunHay80Testdownloadjbhuang0604
BSD300Train/Valdownload 
BSD500Train/Valdownload 
91-ImageTraindownloadYang
DIV2K2017Train/ValwebsiteNTIRE2017
Flickr2KTraindownload 
Real SRTrain/ValwebsiteNTIRE2019
WaterlooTrainwebsite 
VID4Testdownload4 videos
MCL-VTrainwebsite12 videos
GOPROTrain/Valwebsite33 videos, deblur
CelebATrainwebsiteHuman faces
SintelTrain/ValwebsiteOptical flow
FlyingChairsTrainwebsiteOptical flow
Vimeo-90kTrain/Testwebsite90k HQ videos
SR-RAWTrain/Testwebsiteraw sensor image dataset
W2STrain/TestarxivA Joint Denoising and Super-Resolution Dataset

Dataset collections

Benckmark and DIV2K: Set5, Set14, B100, Urban100, Manga109, DIV2K2017 include bicubic downsamples with x2,3,4,8

SR_testing_datasets: Test: Set5, Set14, B100, Urban100, Manga109, Historical; Train: T91,General100, BSDS200

paper

Non-DL based approach

SCSR: TIP2010, Jianchao Yang et al.papercode

ANR: ICCV2013, Radu Timofte et al. papercode

A+: ACCV 2014, Radu Timofte et al. papercode

IA: CVPR2016, Radu Timofte et al. paper

SelfExSR: CVPR2015, Jia-Bin Huang et al. papercode

NBSRF: ICCV2015, Jordi Salvador et al. paper

RFL: ICCV2015, Samuel Schulter et al papercode

DL based approach

Note this table is referenced from here

2014-2016

ModelPublishedCodeKeywords
SRCNNECCV14KerasKaiming
RAISRarXiv-Google, Pixel 3
ESPCNCVPR16KerasReal time/SISR/VideoSR
VDSRCVPR16MatlabDeep, Residual
DRCNCVPR16MatlabRecurrent

2017

ModelPublishedCodeKeywords
DRRNCVPR17CaffePyTorchRecurrent
LapSRNCVPR17MatlabHuber loss
IRCNNCVPR17Matlab 
EDSRCVPR17PyTorchNTIRE17 Champion
BTSRNCVPR17-NTIRE17
SelNetCVPR17-NTIRE17
TLSRCVPR17-NTIRE17
SRGANCVPR17Tensorflow1st proposed GAN
VESPCNCVPR17-VideoSR
MemNetICCV17Caffe 
SRDenseNetICCV17-, PyTorchDense
SPMCICCV17TensorflowVideoSR
EnhanceNetICCV17TensorFlowPerceptual Loss
PRSRICCV17TensorFlowan extension of PixelCNN
AffGANICLR17- 

2018

ModelPublishedCodeKeywords
MS-LapSRNTPAMI18MatlabFast LapSRN
DCSCNarXivTensorflow 
IDNCVPR18CaffeFast
DSRNCVPR18TensorFlowDual state,Recurrent
RDNCVPR18TorchDeep, BI-BD-DN
SRMDCVPR18MatlabDenoise/Deblur/SR
xUnitCVPR18PyTorchSpatial Activation Function
DBPNCVPR18PyTorchNTIRE18 Champion
WDSRCVPR18PyTorchTensorFlowNTIRE18 Champion
ProSRNCVPR18PyTorchNTIRE18
ZSSRCVPR18TensorflowZero-shot
FRVSRCVPR18PDFVideoSR
DUFCVPR18TensorflowVideoSR
TDANarXiv-VideoSR,Deformable Align
SFTGANCVPR18PyTorch 
CARNECCV18PyTorchLightweight
RCANECCV18PyTorchDeep, BI-BD-DN
MSRNECCV18PyTorch 
SRFeatECCV18TensorflowGAN
TSRNECCV18Pytorch 
ESRGANECCV18PyTorchPRIM18 region 3 Champion
EPSRECCV18PyTorchPRIM18 region 1 Champion
PESRECCV18PyTorchECCV18 workshop
FEQEECCV18TensorflowFast
NLRNNIPS18TensorflowNon-local, Recurrent
SRCliqueNetNIPS18-Wavelet
CBDNetarXivMatlabBlind-denoise
TecoGANarXivTensorflowVideoSR GAN

2019

ModelPublishedCodeKeywords
RBPNCVPR19PyTorchVideoSR
SRFBNCVPR19PyTorchFeedback
AdaFMCVPR19PyTorchAdaptive Feature Modification Layers
MoreMNASarXiv-Lightweight,NAS
FALSRarXivTensorFlowLightweight,NAS
Meta-SRCVPR19PyTorchArbitrary Magnification
AWSRNarXivPyTorchLightweight
OISRCVPR19PyTorchODE-inspired Network
DPSRCVPR19PyTorch 
DNICVPR19PyTorch 
MAANetarXiv Multi-view Aware Attention
RNANICLR19PyTorchResidual Non-local Attention
FSTRNCVPR19-VideoSR, fast spatio-temporal residual block
MsDNNarXivTensorFlowNTIRE19 real SR 21th place
SANCVPR19PytorchSecond-order Attention,cvpr19 oral
EDVRCVPRW19PytorchVideo, NTIRE19 video restoration and enhancement champions
Ensemble for VSRCVPRW19-VideoSR, NTIRE19 video SR 2nd place
TENetarXivPytorcha Joint Solution for Demosaicking, Denoising and Super-Resolution
MCANarXivPytorchMatrix-in-matrix CAN, Lightweight
IKC&SFTMDCVPR19-Blind Super-Resolution
SRNTTCVPR19TensorFlowNeural Texture Transfer
RawSRCVPR19TensorFlowReal Scene Super-Resolution, Raw Images
resLFCVPR19 Light field
CameraSRCVPR19 realistic image SR
ORDSRTIPmodelDCT domain SR
U-NetCVPRW19 NTIRE19 real SR 2nd place, U-Net,MixUp,Synthesis
DRLNarxiv Densely Residual Laplacian Super-Resolution
EDRNCVPRW19PytorchNTIRE19 real SR 9th places
FC2NarXiv Fully Channel-Concatenated
GMFNBMVC2019PytorchGated Multiple Feedback
CNN&TV-TV MinimizationBMVC2019 TV-TV Minimization
HRANarXiv Hybrid Residual Attention Network
PPONarXivcodeProgressive Perception-Oriented Network
SROBBICCV19 Targeted Perceptual Loss
RankSRGANICCV19PyTorchoral, rank-content loss
edge-informedICCVW19PyTorchEdge-Informed Single Image Super-Resolution
s-LWSRarxiv Lightweight
DNLNarxiv Video SR Deformable Non-local Network
MGANarxiv Multi-grained Attention Networks
IMDNACM MM 2019PyTorchAIM19 Champion
ESRNarxiv NAS
PFNLICCV19TensorflowVideoSR oral,Non-Local Spatio-Temporal Correlations
EBRNICCV19 Embedded Block Residual Network
Deep SR-ITMICCV19matlabSDR to HDR, 4K SR
feature SRICCV19 Super-Resolution for Small Object Detection
STFANICCV19PyTorchVideo Deblurring
KMSRICCV19PyTorchGAN for blur-kernel estimation
CFSNetICCV19PyTorchControllable Feature
FSRnetICCV19 Multi-bin Trainable Linear Units
SAM+VAMICCVW19  
SinGANICCV19PyTorchbestpaper, train from single image

2020

ModelPublishedCodeKeywords
FISRAAAI 2020TensorFlowVideo joint VFI-SR method,Multi-scale Temporal Loss
ADCSRarxiv  
SCNAAAI 2020 Scale-wise Convolution
LSRGANarxiv Latent Space Regularization for srgan
Zooming Slow-MoCVPR 2020PyTorchjoint VFI and SR,one-stage, deformable ConvLSTM
MZSRCVPR 2020 Meta-Transfer Learning, Zero-Shot
VESR-Netarxiv Youku Video Enhancement and Super-Resolution Challenge Champion
blindvsrarxivPyTorchMotion blur estimation
HNAS-SRarxivPyTorchHierarchical Neural Architecture Search, Lightweight
DRNCVPR 2020PyTorchDual Regression, SISR STOA
SFMarxivPyTorchStochastic Frequency Masking, Improve method
EventSRCVPR 2020 split three phases
USRNetCVPR 2020PyTorch 
PULSECVPR 2020 Self-Supervised
SPSRCVPR 2020CodeGradient Guidance, GAN
DASRarxivCodeReal-World Image Super-Resolution, Unsupervised SuperResolution, Domain Adaptation.
STVUNarxivPyTorchVideo Super-Resolution, Video Frame Interpolation, Joint space-time upsampling
AdaDSRarxivPyTorchAdaptive Inference
Scale-Arbitrary SRarxivCodeScale-Arbitrary Super-Resolution, Knowledge Transfer
DeepSEEarxivCodeExtreme super-resolution,32× magnification
CutBlurCVPR 2020PyTorchSR Data Augmentation
UDVDCVPR 2020 Unified Dynamic Convolutional,SISR and denoise
DINIJCAI-PRICAI 2020 SISR,asymmetric co-attention
PANetarxivPyTorchPyramid Attention
SRResCGANarxivPyTorch 
dSRVAE[]  

Super Resolution workshop papers

NTIRE17 papers

NTIRE18 papers

PIRM18 Web

NTIRE19 papers

AIM19 papers

NTIRE20 NTIRE 2020

---Image and Video Deblurring

---Perceptual Extreme Super-Resolution

---Real-World Image Super-Resolution

Super Resolution survey

[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

  • 1
    点赞
  • 8
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 2
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

芝麻开花666

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值