Skip to content

Latest commit

 

History

History
830 lines (620 loc) · 65.6 KB

ImageRestoration.md

File metadata and controls

830 lines (620 loc) · 65.6 KB

Table of Contents

Image Restoration

  • InstructIR: High-Quality Image Restoration Following Human Instructions
    Marcos V. Conde, Gregor Geigle, Radu Timofte
    [ECCV 2024] [Pytorch-Code]

  • Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild
    Fanghua, Yu, Jinjin Gu, Zheyuan Li, Jinfan Hu, Xiangtao Kong, Xintao Wang, Jingwen He, Yu Qiao, Chao Dong
    [CVPR 2024] [Project] [Pytorch-Code]
    [SUPIR] 🔥

  • MambaIR: A Simple Baseline for Image Restoration with State-Space Model
    Hang Guo, Jinmin Li, Tao Dai, Zhihao Ouyang, Xudong Ren, Shu-Tao Xia
    [ECCV2024] [Pytorch-Code]

  • Image Restoration with Mean-Reverting Stochastic Differential Equations
    Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao, Jens Sjölund, Thomas B. Schön
    [ICML 2023] [Pytorch-Code]
    [IC-SDE]

  • High-resolution Document Shadow Removal via A Large-scale Real-world Dataset and A Frequency-aware Shadow Erasing Net
    Zinuo Li, Xuhang Chen, Chi-Man Pun, Xiaodong Cun
    [ICCV 2023] [Project] [Pytorch-Code]

  • Multi-weather Image Restoration via Domain Translation
    Prashant W Patil, Sunil Gupta, Santu Rana, Svetha Venkatesh, Subrahmanyam Murala
    [ICCV 2023] [Pytorch-Code]

  • DiffIR: Efficient diffusion model for image restoration
    Bin Xia, Yulun Zhang, Shiyin Wang, Yitong Wang, Xinglong Wu, Yapeng Tian, Wenming Yang, Luc Van Gool
    [ICCV 2023] [Pytorch-Code]

  • Focal Network for Image Restoration
    Yuning Cui, Wenqi Ren, Xiaochun Cao, Alois Knoll
    [ICCV 2023] [Pytorch-Code]

  • Under-Display Camera Image Restoration with Scattering Effect
    Binbin Song, Xiangyu Chen, Shuning Xu, Jiantao Zhou
    [ICCV 2023] [Pytorch-Code]
    [UDC]

  • Parallel Diffusion Model of Operator and Image for Blind Inverse Problems
    Hyungjin Chung, Jeongsol Kim, Sehui Kim, Jong Chul Ye
    [CVPR 2023] [Project] [Pytorch-Code]

  • GamutMLP - A Lightweight MLP for Color Loss Recovery
    Hoang M. Le , Brian Price, Scott Cohen, Michael S. Brown
    [CVPR 2023] [Project] [Pytorch-Code]

  • Document Image Shadow Removal Guided by Color-Aware Background
    Ling Zhang, Yinghao He, Qing Zhang, Zheng Liu, Xiaolong Zhang, Chunxia Xiao
    [CVPR 2023] [Pytorch-Code]

  • ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal
    Lanqing Guo, Chong Wang, Wenhan Yang, Siyu Huang, Yufei Wang, Hanspeter Pfister, Bihan Wen
    [CVPR 2023] [Pytorch-Code]

  • Efficient and Explicit Modelling of Image Hierarchies for Image Restoration
    Yawei Li, Yuchen Fan, Xiaoyu Xiang, Denis Demandolx, Rakesh Ranjan, Radu Timofte, Luc Van Gool
    [CVPR 2023] [Pytorch-Code]
    [GRL]

  • Burstormer: Burst Image Restoration and Enhancement Transformer
    Akshay Dudhane, Syed Waqas Zamir, Salman Khan, Fahad Shahbaz Khan, Ming-Hsuan Yang
    [CVPR 2023] [Pytorch-Code]

  • Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bank
    Shirui Huang, Keyan Wang, Huan Liu, Jun Chen, Yunsong Li
    [CVPR 2023] [Pytorch-Code]

  • TAPE: Task-Agnostic Prior Embedding for Image Restoration
    Lin Liu, Lingxi Xie, Xiaopeng Zhang, Shanxin Yuan, Xiangyu Chen, Wengang Zhou, Houqiang Li, Qi Tian
    [ECCV 2022] [Project]

  • Improving Image Restoration by Revisiting Global Information Aggregation
    Xiaojie Chu, Liangyu Chen, Chengpeng Chen, Xin Lu
    [ECCV 2022] [Pytorch-Code]
    [TLC]

  • D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration
    Yuzhi Zhao, Yongzhe Xu, Qiong Yan, Dingdong Yang, Xuehui Wang, Lai-Man Po
    [ECCV 2022] [Pytorch-Code]

  • Simple baselines for image restoration
    Liangyu Chen, Xiaojie Chu, Xiangyu Zhang, Jian Sun
    [ECCV 2022] [Pytorch-Code]
    [NAFNet]

  • Learning Multiple Adverse Weather Removal via Two-stage Knowledge Learning and Multi-contrastive Regularization: Toward a Unified Model
    Wei-Ting Chen, Zhi-Kai Huang, Cheng-Che Tsai, Hao-Hsiang Yang, Jian-Jiun Ding, Sy-Yen Kuo
    [CVPR 2022] [Pytorch-Code]

  • TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions
    Jeya Maria Jose, Rajeev Yasarla, Vishal M. Patel
    [CVPR 2022] [Project] [Pytorch-Code]

  • Attentive Fine-Grained Structured Sparsity for Image Restoration
    Junghun Oh, Heewon Kim, Seungjun Nah, Cheeun Hong, Jonghyun Choi, Kyoung Mu Lee
    [CVPR 2022] [Pytorch-Code]

  • Deep Generalized Unfolding Networks for Image Restoration
    Chong Mou, Qian Wang, Jian Zhang
    [CVPR 2022] [Pytorch-Code]

  • All-In-One Image Restoration for Unknown Corruption
    Boyun Li, Xiao Liu, Peng Hu, Zhongqin Wu, Jiancheng Lv, Xi Peng
    [CVPR 2022] [Pytorch-Code]
    [AirNet] [★] 无需退化先验的图像修复, 利用对比学习提取退化信息, 并引导图像修复.

  • A Differentiable Two-stage Alignment Scheme for Burst Image Reconstruction with Large Shift
    Shi Guo, Xi Yang, Jianqi Ma, Gaofeng Ren, Lei Zhang
    [CVPR 2022] [Pytorch-Code]

  • Burst Image Restoration and Enhancement
    Akshay Dudhane, Syed Waqas Zamir, Salman Khan, Fahad Shahbaz Khan, Ming-Hsuan Yang
    [CVPR 2022 Oral] [Pytorch-Code]
    [BIPNet]

  • Uformer: A General U-Shaped Transformer for Image Restoration
    Zhendong Wang, Xiaodong Cun, Jianmin Bao, Wengang Zhou, Jianzhuang Liu, Houqiang Li
    [CVPR 2022] [Pytorch-Code]

  • Restormer: Efficient Transformer for High-Resolution Image Restoration
    Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang
    [CVPR 2022 Oral] [Pytorch-Code]

  • Residual-Guided Multiscale Fusion Network for Bit-Depth Enhancement
    Jing Liu , Xin Wen, Weizhi Nie, Yuting Su, Peiguang Jing, Xiaokang Yang
    [CSVT 2021]
    [★]

  • SwinIR: Image Restoration Using Swin Transformer
    Jingyun Liang, Jiezhang Cao, Guolei Sun, Kai Zhang, Luc Van Gool, Radu Timofte
    [ICCVW 2021] [Pytorch-Code]
    🔥

  • Learning Dual Priors for JPEG Compression Artifacts Removal
    Xueyang Fu, Xi Wang, Aiping Liu, Junwei Han, Zheng-Jun Zha
    [ICCV 2021] [TF-Code]

  • Towards Flexible Blind JPEG Artifacts Removal
    Jiaxi Jiang, Kai Zhang, Radu Timofte
    [ICCV 2021] [Pytorch-Code]
    [FBCNN]

  • From Shadow Generation to Shadow Removal
    Zhihao Liu, Hui Yin, Xinyi Wu, Zhenyao Wu, Yang Mi, Song Wang
    [CVPR 2021] [PyTorch-Code]
    [G2R-ShadowNet]

  • Auto-exposure fusion for single-image shadow removal
    Lan Fu, Changqing Zhou, Qing Guo, Felix Juefei-Xu, Hongkai Yu, Wei Feng, Yang Liu, Song Wang
    [CVPR 2021] [PyTorch-Code]

  • Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration
    Liyuan Pan, Shah Chowdhury, Richard Hartley, Miaomiao Liu, Hongguang Zhang, Hongdong Li
    [CVPR 2021 Oral] [Code]

  • Controllable Image Restoration for Under-Display Camera in Smartphones
    Kinam Kwon, Eunhee Kang, Sangwon Lee, Su-Jin Lee, Hyong-Euk Lee, ByungIn Yoo, Jae-Joon Han
    [CVPR 2021]
    [UDC]

  • Removing Diffraction Image Artifacts in Under-Display Camera via Dynamic Skip Connection Networks
    Ruicheng Feng, Chongyi Li, Huaijin Chen, Shuai Li, Chen Change Loy, Jinwei Gu
    [CVPR 2021] [Project] [Pytorch-Code]
    [DISCNet] [★★] (UDC图像修复) 使用中兴UDC相机, 模拟Point Spread Function(PSF), 并生成数据集. 网络使用动态卷积, 并加入PSF kernel, 为模型提供先验信息.

  • Image Restoration for Under-Display Camera
    Yuqian Zhou, David Ren, Neil Emerton, Sehoon Lim, Timothy Large
    [CVPR 2021] [Project]
    [UDC]

  • Multi-Stage Progressive Image Restoration
    Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, Ling Shao
    [CVPR 2021] [Pytorch-Code]
    [MPRNet] [🔥] 多阶段结构, 用了attention等一些trick

  • COLA-Net: Collaborative Attention Network for Image Restoration
    Chong Mou, Jian Zhang, Xiaopeng Fan, Hangfan Liu, Ronggang Wang
    [MM 2021] [Project]

  • Pyramid Attention Networks for Image Restoration
    Kai Zhang, Yawei Li, Wangmeng Zuo, Lei Zhang, Luc Van Gool, Radu Timofte,
    [TPAMI 2021] [Pytorch-Code]
    [DPIR]

  • Pyramid Attention Networks for Image Restoration
    Yiqun Mei, Yuchen Fan, Yulun Zhang, Jiahui Yu, Yuqian Zhou, Ding Liu, Yun Fu, Thomas S. Huang, Humphrey Shi
    [arXiv 2004] [Pytorch-Code]
    [PANet]

  • Neural Sparse Representation for Image Restoration
    Yuchen Fan, Jiahui Yu, Yiqun Mei, Yulun Zhang, Yun Fu, Ding Liu, Thomas S. Huang
    [NeurIPS 2020] [Code]
    [NSR]

  • Scale-wise Convolution for Image Restoration
    Yuchen Fan, Jiahui Yu, Ding Liu, Thomas S. Huang
    [AAAI 2020] [Pytorch-Code]
    [SCN]

  • Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
    Xingang Pan, Xiaohang Zhan, Bo Dai, Dahua Lin, Chen Change Loy, Ping Luo
    [ECCV 2020 Oral] [Pytorch-Code]
    [DGP] [★★] 提出用预训练的GAN作为先验, 无需在特定任务上finetune, 即可实现超分, 上色等图像恢复任务和图像变形，类别转换等图像编辑功能. 论文主要是在一般GAN inversion的基础上, 提出同时优化隐向量z和生成网络参数, 达到了更好更自然的效果.

  • Stacking Networks Dynamically for Image Restoration Based on the Plug-and-Play Framework
    Haixin Wang, Tianhao Zhang, Muzhi Yu, Jinan Sun, Wei Ye, Chen Wang, Shikun Zhang
    [ECCV 2020]

  • Blind Image Restoration without Prior Knowledge
    Noam Elron, Shahar S. Yuval, Dmitry Rudoy, Noam Lev
    [ECCV 2020]
    [SNSC] [★] 提出了一个Self-Normalization Side-Chain模块, 用来提取全局信息

  • LIRA: Lifelong Image Restoration from Unknown Blended Distortions
    Jianzhao Liu, Jianxin Lin, Xin Li, Wei Zhou, Sen Liu, Zhibo Chen
    [ECCV 2020]

  • Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration
    Jingwen He, Chao Dong, Yu Qiao
    [ECCV 2020] [Pytorch-Code]
    [CResMD] [★] (控制restoration level) 将控制参数由一个扩展为多个, 处理不同种类不同程度的退化, 输入的参数由若干FC层处理为权值vector, 作为残差块中的卷积分支的scale. 提出了一些trick训练不同退化的数据. 虽然论文表示可以处理多种退化情形, 但是用户手动调节两个甚至更多参数还是挺麻烦的.

  • Microscopy Image Restoration with Deep Wiener-Kolmogorov filters
    Valeriya Pronina, Filippos Kokkinos, Dmitry V. Dylov, Stamatios Lefkimmiatis
    [ECCV 2020] [Project] [Pytorch-Code]

  • Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration
    Bruno Lecouat, Jean Ponce, Julien Mairal
    [ECCV 2020] [Pytorch-Code]
    [GroupSC]

  • Learning Disentangled Feature Representation for Hybrid-distorted Image Restoration
    Xin Li, Xin Jin, Jianxin Lin, Tao Yu, Sen Liu, Yaojun Wu, Wei Zhou, Zhibo Chen
    [ECCV 2020]
    [★] (处理多种退化) 大致浏览, 通过gain-control-based normalization学习解耦特征, 并据此设计了几个模块, 处理多种退化混合问题. 文中使用了spectral value di�erence orthogonality regularization作为一个loss, 促使feature map直接学到不相关的信息.

  • Learning Enriched Features for Real Image Restoration and Enhancement
    Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, Ling Shao
    [ECCV 2020] [Pytorch-Code]
    [MIRNet] [★] 提出了一个就多尺度特征融合的网络用于去噪, 超分, 增强等任务. 使用attention的思想设计了很多模块, 性能不错, 在各种任务上适用性看起来较强

  • Bringing Old Photos Back to Life
    Ziyu Wan, Bo Zhang, Dongdong Chen, Pan Zhang, Dong Chen, Jing Liao, Fang Wen
    [CVPR 2020 Oral] [Project]
    [★★☆] (无监督, domain transfer) 无监督老照片恢复, 用生成的老照片训练, 在真实老照片上取得好效果. 使用一个VAE将真实和生成的照片映射到相近的空间, 第二个VAE负责恢复无损照片, 中间还有一些映射等操作.

  • Fast Underwater Image Enhancement for Improved Visual Perception
    Md Jahidul Islam, Youya Xia, Junaed Sattar
    [RAL 2020] [Code]
    [FUnIE-GAN] [★] encoder-decoder结构, 使用了几个目标函数从各方面增强图像视觉质量. 提出了一个水下图像数据集.

  • Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration
    Xing Liu, Masanori Suganuma, Zhun Sun, Takayuki Okatani
    [CVPR 2019] [Code]
    [DuRN] [★☆] 1) 文章提出, 许多图像复原任务都由一些成对的模块组成, 比如去噪里的大kernel和小kernel, 超分里的下采样和上采样. 本文在residual connection的基础上, 进一步给每个模块内部的操作直接加入residual connection, 增加了组合数. 2) 在去噪, 去模糊, 去雾等任务中都取得了不错的效果.

  • Attention-based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions
    Masanori Suganuma, Xing Liu, Takayuki Okatani
    [CVPR 2019] [Code]
    [★☆] (处理多种退化) 提出用一个基于attention的操作加权网络, 用来处理不同种类的degradation. 性能一般, 不太容易收敛, 思路值得借鉴.

  • Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers
    Jingwen He, Chao Dong, Yu Qiao
    [CVPR 2019] [Pytorch-Code]
    [AdaFM] [★☆] (控制restoration level) 提出了一个AdaFM模块, 用于控制网络对图像的修复程度. AdaFM模块实际上就是一个dw conv层, 通过手动控制该层的权重, 达到控制修复程度的目的. 论文这么做是基于两个发现: 1) 对于不同restoration level, 网络提取的visual patterns是相似的, 只是weights不同; 2)调整网络内部参数对输出的影响是连续的.

  • CFSNet: Toward a Controllable Feature Space for Image Restoration
    Wei Wang, Ruiming Guo, Yapeng Tian, Wenming Yang
    [ICCV 2019] [Pytorch-Code]
    [★] (控制restoration level) 粗读, 用一个手动输入的参数控制两个分支的权重, 一个分支负责low distortion修复, 另一个分支负责high visual quality. 两个分支通过使用不同loss (L1, L2 v.s. vgg, GAN loss) 训练来得到. 文章的效果和实用性有待检验, 思路可借鉴.

  • Gated Context Aggregation Network for Image Dehazing and Deraining
    Dongdong Chen, Mingming He, Qingnan Fan
    [WACV 2019] [Code]
    [GCANet] [★] 在dilation卷积前加入可分离卷积, 消除grid effect. 除去雾去雨外应该也适合其它任务.

  • Learning Dual Convolutional Neural Networks for Low-Level Vision
    Jinshan Pan, Sifei Liu, Deqing Sun, Jiawei Zhang, Yang Liu, Jimmy Ren, Zechao Li, Jinhui Tang, Huchuan Lu, Yu-Wing Tai, Ming-Hsuan Yang
    [CVPR 2018] [Project] [Unofficial-TF-Code]
    [DualCNN] [★] 粗读, 设计了一双分支网络, 一个学习detail, 一个学习structure, 针对任务对两个分支也分别进行监督训练

  • Deep Image Prior
    Dmitry Ulyanov, Andrea Vedald, Victor Lempitsky
    [CVPR 2018] [Project]
    [★★] (zero-shot) 1) 一篇有趣的论文, 提出深度卷积网络在图像生成和恢复任务中表现好的原因, 可能并不是因为其从大量图像中学习到了某种先验, 其实随机初始化的网络足以从输入中抓取大量的low-level图像先验信息. 在通过迭代的方式从图像中学习先验的过程中, 那些自然的, 有规律的内容较容易提取,会先被学习出来, 因此就达到了去噪或其它restoration的目的. 2) 粗读, 实用性有待验证, 有时间可以好好研究一下.

  • Image Companding and Inverse Halftoning using Deep Convolutional Neural Networks
    Xianxu Hou, Guoping Qiu
    [arXiv 1707]
    [★] CNN做Image Companding和Inverse Halftoning

Image Dehazing

Image Debluring

  • Deblurring 3D Gaussian Splatting
    Byeonghyeon Lee, Howoong Lee, Xiangyu Sun, Usman Ali, Eunbyung Park
    [ECCV 2024] [Pytorch-Code]

  • BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splatting
    Lingzhe Zhao, Peng Wang, Peidong Liu
    [ECCV 2024] [Pytorch-Code]

  • Efficient Frequency Domain-Based Transformers for High-Quality Image Deblurring
    Lingshun Kong, Jiangxin Dong, Jianjun Ge, Mingqiang Li, Jinshan Pan
    [CVPR 2023] [Project]
    [FFTformer]

  • Hybrid Neural Rendering for Large-Scale Scenes with Motion Blur
    Peng Dai, Yinda Zhang, Xin Yu, Xiaoyang Lyu, Xiaojuan Qi
    [CVPR 2023] [Project] [Pytorch-Code]

  • Blur Interpolation Transformer for Real-World Motion from Blur
    Lingshun Kong, Jiangxin Dong, Jianjun Ge, Mingqiang Li, Jinshan Pan
    [CVPR 2023] [Pytorch-Code]

  • Blur Interpolation Transformer for Real-World Motion from Blur
    Zhihang Zhong, Mingdeng Cao, Xiang Ji, Yinqiang Zheng, Imari Sato
    [CVPR 2023] [Project] [Pytorch-Code]

  • Structured Kernel Estimation for Photon-Limited Deconvolution
    Yash Sanghvi, Zhiyuan Mao, Stanley H. Chan
    [CVPR 2023] [Project] [Pytorch-Code]

  • Fast Two-step Blind Optical Aberration Correction
    Thomas Eboli, Jean-Michel Morel, Gabriele Facciolo
    [ECCV 2022] [Project] [Code]

  • Learning to Deblur using Light Field Generated and Real Defocus Images
    Lingyan Ruan, Bin Chen, Jizhou Li, Miuling Lam
    [CVPR 2022 Oral] [Project] [Pytorch-Code]
    [DRBNet]

  • E-CIR: Event-Enhanced Continuous Intensity Recovery
    Chen Song, Qixing Huang, Chandrajit Bajaj
    [CVPR 2022] [Pytorch-Code]

  • Polyblur: Removing mild blur by polynomial reblurring
    Mauricio Delbracio, Ignacio Garcia-Dorado, Sungjoon Choi, Damien Kelly, Peyman Milanfar
    [TCI 2021] [Google]

  • Explore Image Deblurring via Encoded Blur Kernel Space
    P.Tran, A.Tran, Q.Phung, M. Hoai
    [CVPR 2021] [Pytorch-Code]

  • Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes
    Zhihang Zhong, Yinqiang Zheng, Imari Sato
    [CVPR 2021] [Pytorch-Code]
    [RSCD]

  • DeFMO: Deblurring and Shape Recovery of Fast Moving Objects
    Denys Rozumnyi, Martin R. Oswald, Vittorio Ferrari, Jiri Matas, Marc Pollefeys
    [CVPR 2021] [Pytorch-Code]

  • Learning a Non-blind Deblurring Network for Night Blurry Images
    Liang Chen, Jiawei Zhang, Jinshan Pan, Songnan Lin, Faming Fang, Jimmy Ren
    [CVPR 2021]

  • Deblurring by Realistic Blurring
    Kaihao Zhang, Wenhan Luo, Yiran Zhong, Lin Ma, Bjorn Stenger, Wei Liu, Hongdong Li
    [CVPR 2020]

  • Learning Event-Based Motion Deblurring
    Zhe Jiang, Yu Zhang, Dongqing Zou, Jimmy Ren, Jiancheng Lv, Yebin Liu
    [CVPR 2020]

  • Efficient Dynamic Scene Deblurring Using Spatially Variant Deconvolution Network With Optical Flow Guided Training
    Yuan Yuan, Wei Su, Dandan Ma
    [CVPR 2020]

  • Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring
    Maitreya Suin, Kuldeep Purohit, A. N. Rajagopalan
    [CVPR 2020]

  • Variational-EM-Based Deep Learning for Noise-Blind Image Deblurring
    Yuesong Nan, Yuhui Quan, Hui Ji
    [CVPR 2020]

  • Deblurring Using Analysis-Synthesis Networks Pair
    Adam Kaufman, Raanan Fattal
    [CVPR 2020]

  • Deep Learning for Handling Kernel/model Uncertainty in Image Deconvolution
    Yuesong Nan, Hui Ji
    [CVPR 2020]

  • All in One Bad Weather Removal using Architectural Search
    Ruoteng Li, Robby T. Tan, Loong-Fah Cheong
    [CVPR 2020]

  • DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
    Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang
    [ICCV 2019] [Pytorch-Code]
    [★☆] DeblurGAN基础上的改进, 把生成网络换成了FPN, 设计了新的loss, 效果更快更好了

  • Gyroscope-Aided Motion Deblurring with Deep Network
    Janne Mustaniemi, Juho Kannala, Simo Särkkä, [J]iri Matas](https://cmp.felk.cvut.cz/~matas/), Janne Heikkilä
    [WACV 2019]
    [DeepGyro] [★] 结合陀螺仪作为先验deblur. 从陀螺仪和图像拍摄信息生成训练集的方法可以参考.

  • Douglas-Rachford Networks: Learning Both the Image Prior and Data Fidelity Terms for Blind Image Deconvolution
    Raied Aljadaany, Dipan K. Pal, Marios Savvides
    [CVPR 2019]
    [Dr-Net] [★☆] 1) 基于Douglas-Rachford迭代优化求解blind deconvolution的思路(不懂), 提出了一个由简单conv和连接操作组成的Dr Block, 将其嵌入普通卷积网络中, 用L2和GAN loss训练, 取得了不错的效果. 2) 网络细节没看, 可以借鉴其模块设计

  • Deep Stacked Multi-patch Hierarchical Network for Image Deblurring
    Hongguang Zhang, Yuchao Dai, Hongdong Li, Piotr Koniusz
    [CVPR 2019] [Pytorch-Code]
    [DMPHN] [☆] 从spatial pyramid matching的角度出发, 提出了一个分patch的逐层融合处理的网络, 参数少速度快. 但个人仍不理解这种分patch的做法对CNN来说到底有什么意义.

  • Human-Aware Motion Deblurring
    Ziyi Shen, Wenguan Wang, Xiankai Lu, Jianbin Shen, Haibin Ling, Tingfa Xu, Ling Shao
    [ICCV 2019] [Project] [HIDE Dataset]
    [HA-Deblur] [★☆] 1. 提出了HIDE数据集, 主要关注对人体的deblur. 2. 提出了一个多分支deblur网络, 根据human-aware子网络预测前背景生成weight map, 将多分枝信息融合处理后输出

  • A Deep Encoder-Decoder Network For Joint Deblurring and Super-Resolution
    Xinyi Zhang, Fei Wang, Hang Dong, Yu Guo
    [ICASSP 2018] [Project]
    [ED-DSRN] [☆] 大致浏览, 一个端到端的同时deblur和超分网络

  • Gated Fusion Network for Joint Image Deblurring and Super-Resolution
    Xinyi Zhang, Hang Dong, Zhe Hu, Wei-Sheng Lai, Fei Wang, Ming-Hsuan Yang
    [BMVC 2018] [Project] [Pytorch-Code]
    [GFN] [★☆] 1) 提出了一个同时做deblur和超分的网络. 网络有两个分支, 一个encoder-decoder结构做deblur, 一个不降分辨率做SR, 用一个几层卷积组成的gate模块选择特征. 2) 思路简单, 可以尝试.

  • DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
    Orest Kupyn, Volodymyr Budzan, Mykola Mykhailych, Dmytro Mishkin, Jiří Matas
    [CVPR 2018] [Pytorch-Code] [Unofficial-TF-Code1] [Unofficial-TF-Code2]
    [★★] 1) 用GAN做deblur的一篇典型文章, 效果不错. 2) 生成网络结构简单, 采用残差形式. 3) 提出了生成blur数据的方法, 可以参考一下.

  • Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
    Seungjun Nah, Tae Hyun Kim, Kyoung Mu Lee
    [CVPR 2017 Spotlight] [Code]
    [★☆] 1) 提出了GOPRO单张图像deblur数据集. 2) 提出了一个多尺度输入的去噪网络

Reflection Removal

Image Inpainting

De-raining

  • Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks
    Sixiang Chen, Tian Ye, Jinbin Bai, Erkang Chen, Jun Shi, Lei Zhu
    [ICCV 2023] [Project] [Pytorch-Code]

  • Learning A Sparse Transformer Network for Effective Image Deraining
    Xiang Chen, Hao Li, Mingqiang Li, Jinshan Pan
    [CVPR 2023] [Pytorch-Code]
    [DRSformer]

  • Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond
    Yi Yu, Wenhan Yang, Yap-Peng Tan, Alex C. Kot
    [CVPR 2022] [Pytorch-Code]

  • Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation
    Yuntong Ye, Yi Chang, Hanyu Zhou, Luxin Yan
    [CVPR 2021] [Pytorch-Code]
    [JRGR]

  • Removing Raindrops and Rain Streaks in One Go
    Ruijie Quan, Xin Yu, Yuanzhi Liang, Yi Yang
    [CVPR 2021]
    [CCN]

  • From Rain Generation to Rain Removal
    Hong Wang, Zongsheng Yue, Qi Xie, Qian Zhao, Yefeng Zheng, Deyu Meng
    [CVPR 2021] [Pytorch-Code]
    [VRGNet]

  • Syn2Real Transfer Learning for Image Deraining using Gaussian Processes
    Rajeev Yasarla, Vishwanath A. Sindagi, Vishal M. Patel
    [CVPR 2020] [Pytorch-Code]
    [★★] 使用高斯过程计算无标签真实数据的unsupervised loss. 从paper的实验效果来看有不错的效果, 值得一试

  • Multi-Scale Progressive Fusion Network for Single Image Deraining
    Kui Jiang, Zhongyuan Wang, Peng Yi, Chen Chen, Baojin Huang, Yimin Luo, Jiayi Ma, Junjun Jiang
    [CVPR 2020] [TF-Code]
    [MSPFN]

  • Detail-recovery Image Deraining via Context Aggregation Networks
    Sen Deng, Mingqiang Wei, Jun Wang, Yidan Feng, Luming Liang, Haoran Xie, Fu Lee Wang, Meng Wang
    [CVPR 2020] [TF-Code]
    [DRD-Net]

  • Density-aware Single Image De-raining using a Multi-stream Dense Network
    He Zhang, Vishal M. Patel
    [CVPR 2018] [Pytorch-Code]
    [DID-MDN] [★☆] 基于dense connection的双分支去雨网络, 一个分支预测一个雨稠密程度的类别标签(大中小), 一个采用残差预测结构, 并结合稠密程度label, 预测去雨图像, 经过一个refinement网络输出. 加入一个预测程度的分支的策略, 在图像增强恢复任务中还是比较值得尝试的.

Image Demoireing

  • Image Demoireing with Learnable Bandpass Filters
    Bolun Zheng, Shanxin Yuan, Gregory Slabaugh, Ales Leonardis
    [CVPR 2020] [TF-Code]
    [★] 在DCT变换后的频谱域做摩尔纹提取, 分为3个scale提取不同尺度的摩尔纹. 对带通去取摩尔纹的推导部分没看懂.

  • Joint Demosaicing and Denoising With Self Guidance
    Lin Liu, Xu Jia, Jianzhuang Liu, Qi Tian
    [CVPR 2020] [Pytorch-Code]
    [JDD]

  • Wavelet-Based Dual-Branch Networkfor Image Demoireing
    [Author]Lin Liu, Jianzhuang Liu, Shanxin Yuan, Gregory Slabaugh, Ales Leonardis, Wengang Zhou, Qi Tian
    [ECCV 2020] [Project]

  • FHDe²Net: Full High Definition Demoireing Network
    Bin He, Ce Wang, Boxin Shi, Ling-Yu Duan
    [ECCV 2020] [Project]

  • Self-Adaptively Learning to Demoiré from Focused and Defocused Image Pairs
    Lin Liu, Shanxin Yuan, Jianzhuang Liu, Liping Bao, Gregory Slabaugh, Qi Tian
    [NeurIPS 2020] [Project]

Image Debanding

  • Fast Blind Decontouring Network
    Yang Zhao, Wei Jia, Yuan Chen, Ronggang Wang
    [TCSVT 2022]
    [★] 预测smooth区域mask, 再对平滑区域做debanding. 训练数据生成使用ALD方法检测gt的平滑区域作为mask真值, 对平滑区域做banding退化. mask预测网络的loss使用了最小化梯度以及mask约束.

  • Deep Image Debanding
    Raymond Zhou, Shahrukh Athar, Zhongling Wang, Zhou Wang
    [arXiv 2110]
    [☆]

  • Deep Reconstruction of Least Significant Bits for Bit-Depth Expansion
    Yang Zhao, Ronggang Wang, Wei Jia, Wangmeng Zuo, Xiaoping Liu, Wen Gao


[TIP 2019]
[★] 低bit位图像恢复到高bit位图像, 主要处理banding问题
  • Real-Time False-Contours Removal for Inverse Tone Mapped HDR Content
    Gonzalo Luzardo, Jan Aelterman, Hiep Luong, Wilfried Philips, Daniel Ochoa
    [MM 2017]
    [★] Signal processing based.