zoukankan      html  css  js  c++  java
  • GitHub:超分辨率最全资料集锦

    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。

    在这里插入图片描述

    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    PDF    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。
    ————————————————
    版权声明:本文为CSDN博主「Amusi(CVer)」的原创文章,遵循CC 4.0 BY-SA版权协议,转载请附上原文出处链接及本声明。
    原文链接:https://blog.csdn.net/amusi1994/article/details/109240491

    _________________________________________________________________________________________________________________________________________________
    每一个不曾起舞的日子,都是对生命的辜负。
    But it is the same with man as with the tree. The more he seeks to rise into the height and light, the more vigorously do his roots struggle earthward, downward, into the dark, the deep - into evil.
    其实人跟树是一样的,越是向往高处的阳光,它的根就越要伸向黑暗的地底。----尼采
  • 相关阅读:
    PTP 接线方式及通讯距离
    串口通信基本概念
    Modbus RTU 通信应用案例
    Modbus 指令
    Modbus RTU新版本指令介绍
    Integer自动装箱和拆箱
    重写hashCode方法,导致内存泄漏
    Dom4j入门
    Java设计模式(9)——观察者模式
    IntelliJ IDEA版本控制——过滤提交文件
  • 原文地址:https://www.cnblogs.com/leoking01/p/14657556.html
Copyright © 2011-2022 走看看