ECCV2020|图像重建/底层视觉(超分辨率,图像恢复,去雨,去雾,去模糊,去噪等)相关论文汇总(附论文链接/开源代码/解析)【持续更新】

ECCV2020|图像重建相关论文汇总(如果觉得有帮助,欢迎点赞和收藏)

  • 1.超分辨率(Super-Resolution)
    • 图像超分辨率
      • Invertible Image Rescaling
      • Component Divide-and-Conquer for Real-World Image Super-Resolution
      • SRFlow: Learning the Super-Resolution Space with Normalizing Flow
      • Single Image Super-Resolution via a Holistic Attention Network
      • Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks
      • VarSR: Variational Super-Resolution Network for Very Low Resolution Images
      • Learning with Privileged Information for Efficient Image Super-Resolution
      • Binarized Neural Network for Single Image Super Resolution
    • 视频超分辨率
      • Across Scales & Across Dimensions: Temporal Super-Resolution using Deep Internal Learning
      • MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution
      • Video Super-Resolution with Recurrent Structure-Detail Network
    • 人脸超分辨率
      • Face Super-Resolution Guided by 3D Facial Priors
    • 深度图超分辨率
    • 光场图像超分辨率
      • Spatial-Angular Interaction for Light Field Image Super-Resolution
    • 高光谱图像超分辨率
      • Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution
    • 零样本超分辨率
      • Zero-Shot Image Super-Resolution with Depth Guided Internal Degradation Learning
      • Fast Adaptation to Super-Resolution Networks via Meta-Learning
    • 文本超分辨率
      • PlugNet: Degradation Aware Scene Text Recognition Supervised by a Pluggable Super-Resolution Unit
      • Scene Text Image Super-Resolution in the Wild
    • 绘画超分辨率
      • Texture Hallucination for Large-Factor Painting Super-Resolution
    • 用于超分辨率的数据增广
    • 超分辨率用于语义分割
    • 超分辨率模型压缩/轻量化
      • Journey Towards Tiny Perceptual Super-Resolution
      • LatticeNet: Towards Lightweight Image Super-resolution with Lattice Block
    • 其他超分(暂存)
      • Towards Content-independent Multi-Reference Super-Resolution: Adaptive Pattern Matching and Feature Aggregation
      • PAMS: Quantized Super-Resolution via Parameterized Max Scale
      • Mining self-similarity: Label super-resolution with epitomic representations
  • 2.图像去雨(Image Deraining)
      • Rethinking Image Deraining via Rain Streaks and Vapors
      • Beyond Monocular Deraining: Paired Rain Removal Networks via Unpaired Semantic Understanding
  • 3.图像去雾(Image Dehazing)
      • HardGAN: A Haze-Aware Representation Distillation GAN for Single Image Dehazing
      • Physics-based Feature Dehazing Networks
  • 4.去模糊(Deblurring)
      • End-to-end Interpretable Learning of Non-blind Image Deblurring
      • Spatio-Temporal Efficient Recurrent Neural Network for Video Deblurring
      • Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training
      • Learning Event-Driven Video Deblurring and Interpolation
      • Defocus Deblurring Using Dual-Pixel Data
      • Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms
      • OID: Outlier Identifying and Discarding in Blind Image Deblurring
      • Enhanced Sparse Model for Blind Deblurring
  • 5.去噪(Denoising)
      • Unpaired Learning of Deep Blind Image Denoising
      • Practical Deep Raw Image Denoising on Mobile Devices
      • Reconstructing the Noise Manifold for Image Denoising
      • Burst Denoising via Temporally Shifted Wavelet Transforms
      • Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks
      • Learning Graph-Convolutional Representations for Point Cloud Denoising
      • Spatial Hierarchy Aware Residual Pyramid Network for Time-of-Flight Depth Denoising
      • A Decoupled Learning Scheme for Real-world Burst Denoising from Raw Images
      • Robust and On-the-fly Dataset Denoising for Image Classification
      • Spatial-Adaptive Network for Single Image Denoising
  • 6.图像恢复(Image Restoration)
      • Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
      • PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration
      • Stacking Networks Dynamically for Image Restoration Based on the Plug-and-Play Framework
      • LIRA: Lifelong Image Restoration from Unknown Blended Distortions
      • Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration
      • Microscopy Image Restoration with Deep Wiener-Kolmogorov filters
      • Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration
      • Learning Enriched Features for Real Image Restoration and Enhancement
      • Learning Disentangled Feature Representation for Hybrid-distorted Image Restoration
  • 7.图像增强(Image Enhancement)
      • URIE: Universal Image Enhancement for Visual Recognition in the Wild
      • Early Exit Or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images
      • Global and Local Enhancement Networks For Paired and Unpaired Image Enhancement
      • PieNet: Personalized Image Enhancement Network
  • 8.图像去摩尔纹(Image Demoireing)
      • Wavelet-Based Dual-Branch Neural Network for Image Demoireing
  • 9.图像修复(Inpainting)
      • Learning Joint Spatial-Temporal Transformations for Video Inpainting
      • Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations
      • High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling
      • Short-Term and Long-Term Context Aggregation Network for Video Inpainting
      • Learning Object Placement by Inpainting for Compositional Data Augmentation
      • High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling
      • DVI: Depth Guided Video Inpainting for Autonomous Driving
      • VCNet: A Robust Approach to Blind Image Inpainting
      • Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes
  • 10.图像质量评价(Image Quality Assessment)
      • GIQA: Generated Image Quality Assessment
      • PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration
  • 参考

整理了下今年ECCV图像重建/底层视觉(Low-Level Vision)相关的一些论文,包括超分辨率,图像恢复,去雨,去雾,去模糊,去噪等方向。大家如果觉得有帮助,欢迎点赞和收藏~~
Github地址见右:Awesome-ECCV2020-Low-Level-Vision,欢迎star~

2020年ECCV(European Conference on Computer Vision)将于8月2日到8月28日在线上召开。目前ECCV2020已经放榜,有效投稿数为5025,最终收录1361篇论文,录取率是27%。其中104篇 Oral、161篇 Spotlights,其余的均为Poster。
ECCV2020的官网:https://eccv2020.eu/
ECCV2020接收论文列表:https://eccv2020.eu/accepted-papers/

1.超分辨率(Super-Resolution)

图像超分辨率

Invertible Image Rescaling

  • Paper:https://arxiv.org/abs/2005.05650
  • Code:https://github.com/pkuxmq/Invertible-Image-Rescaling
  • Homepage:
  • Analysis:ECCV 2020 Oral | 可逆图像缩放:完美恢复降采样后的高清图片

Component Divide-and-Conquer for Real-World Image Super-Resolution

  • Paper:https://arxiv.org/abs/2008.01928
  • Code:https://github.com/xiezw5/Component-Divide-and-Conquer-for-Real-World-Image-Super-Resolution

SRFlow: Learning the Super-Resolution Space with Normalizing Flow

  • Paper:https://arxiv.org/abs/2006.14200?context=eess
  • Code:https://github.com/andreas128/SRFlow

Single Image Super-Resolution via a Holistic Attention Network

  • Analysis:ECCV2020最新图像超分辨重建文章

Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks

  • Paper:https://arxiv.org/abs/2003.07119

VarSR: Variational Super-Resolution Network for Very Low Resolution Images

Learning with Privileged Information for Efficient Image Super-Resolution

  • Paper:https://arxiv.org/abs/2007.07524
  • Code:https://github.com/pkuxmq/Invertible-Image-Rescaling
  • Homepage:https://cvlab.yonsei.ac.kr/projects/PISR/

Binarized Neural Network for Single Image Super Resolution

视频超分辨率

Across Scales & Across Dimensions: Temporal Super-Resolution using Deep Internal Learning

  • Paper:https://arxiv.org/abs/2003.08872
  • Code:
  • Homepage:http://www.wisdom.weizmann.ac.il/~vision/DeepTemporalSR/
  • Analysis:

MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution

  • Paper:https://arxiv.org/abs/2007.11803v1

Video Super-Resolution with Recurrent Structure-Detail Network

  • Paper:https://arxiv.org/abs/2008.00455
  • Code:https://github.com/junpan19/RSDN
  • Homepage:http://www.wisdom.weizmann.ac.il/~vision/DeepTemporalSR/

人脸超分辨率

Face Super-Resolution Guided by 3D Facial Priors

  • Paper:https://arxiv.org/abs/2007.09454v1

深度图超分辨率

光场图像超分辨率

Spatial-Angular Interaction for Light Field Image Super-Resolution

  • Paper:https://arxiv.org/abs/1912.07849
  • Code:https://github.com/YingqianWang/LF-InterNet
  • Presentation:https://wyqdatabase.s3-us-west-1.amazonaws.com/LF-InterNet.mp4
  • Analysis:ECCV 2020 | 空间-角度信息交互的光场图像超分辨,性能优异代码已开源

高光谱图像超分辨率

Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution

  • Paper:https://arxiv.org/abs/2007.05230
  • Code:https://github.com/danfenghong/ECCV2020_CUCaNet

零样本超分辨率

Zero-Shot Image Super-Resolution with Depth Guided Internal Degradation Learning

Fast Adaptation to Super-Resolution Networks via Meta-Learning

  • Paper:https://arxiv.org/abs/2001.02905v1

文本超分辨率

PlugNet: Degradation Aware Scene Text Recognition Supervised by a Pluggable Super-Resolution Unit

  • Analysis:ECCV 2020 | 图匠数据、华中师范提出低质退化文本识别算法PlugNet

Scene Text Image Super-Resolution in the Wild

  • Paper:https://arxiv.org/abs/2005.03341v1
  • Code:https://github.com/JasonBoy1/TextZoom

绘画超分辨率

Texture Hallucination for Large-Factor Painting Super-Resolution

  • Paper:https://arxiv.org/abs/1912.00515?context=eess.IV

用于超分辨率的数据增广

超分辨率用于语义分割

超分辨率模型压缩/轻量化

Journey Towards Tiny Perceptual Super-Resolution

  • Paper:https://arxiv.org/abs/2007.04356

LatticeNet: Towards Lightweight Image Super-resolution with Lattice Block

其他超分(暂存)

Towards Content-independent Multi-Reference Super-Resolution: Adaptive Pattern Matching and Feature Aggregation

PAMS: Quantized Super-Resolution via Parameterized Max Scale

Mining self-similarity: Label super-resolution with epitomic representations

2.图像去雨(Image Deraining)

Rethinking Image Deraining via Rain Streaks and Vapors

  • Paper:https://arxiv.org/abs/2008.00823
  • Code:https://github.com/yluestc/derain

Beyond Monocular Deraining: Paired Rain Removal Networks via Unpaired Semantic Understanding

3.图像去雾(Image Dehazing)

HardGAN: A Haze-Aware Representation Distillation GAN for Single Image Dehazing

Physics-based Feature Dehazing Networks

4.去模糊(Deblurring)

End-to-end Interpretable Learning of Non-blind Image Deblurring

  • Paper:https://arxiv.org/abs/2007.01769
  • Code:

Spatio-Temporal Efficient Recurrent Neural Network for Video Deblurring

Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training

Learning Event-Driven Video Deblurring and Interpolation

Defocus Deblurring Using Dual-Pixel Data

Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms

OID: Outlier Identifying and Discarding in Blind Image Deblurring

Enhanced Sparse Model for Blind Deblurring

5.去噪(Denoising)

Unpaired Learning of Deep Blind Image Denoising

Practical Deep Raw Image Denoising on Mobile Devices

Reconstructing the Noise Manifold for Image Denoising

Burst Denoising via Temporally Shifted Wavelet Transforms

Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks

Learning Graph-Convolutional Representations for Point Cloud Denoising

Spatial Hierarchy Aware Residual Pyramid Network for Time-of-Flight Depth Denoising

A Decoupled Learning Scheme for Real-world Burst Denoising from Raw Images

Robust and On-the-fly Dataset Denoising for Image Classification

Spatial-Adaptive Network for Single Image Denoising

6.图像恢复(Image Restoration)

Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation

  • Paper:https://arxiv.org/abs/2003.13659
  • Code:https://github.com/XingangPan/deep-generative-prior

PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration

Stacking Networks Dynamically for Image Restoration Based on the Plug-and-Play Framework

LIRA: Lifelong Image Restoration from Unknown Blended Distortions

Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration

Microscopy Image Restoration with Deep Wiener-Kolmogorov filters

Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration

Learning Enriched Features for Real Image Restoration and Enhancement

Learning Disentangled Feature Representation for Hybrid-distorted Image Restoration

7.图像增强(Image Enhancement)

URIE: Universal Image Enhancement for Visual Recognition in the Wild

Early Exit Or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images

Global and Local Enhancement Networks For Paired and Unpaired Image Enhancement

PieNet: Personalized Image Enhancement Network

8.图像去摩尔纹(Image Demoireing)

Wavelet-Based Dual-Branch Neural Network for Image Demoireing

  • Paper:https://arxiv.org/abs/2007.07173
  • Analysis:#每日五分钟一读# Image Demoireing

9.图像修复(Inpainting)

Learning Joint Spatial-Temporal Transformations for Video Inpainting

  • Paper:https://arxiv.org/abs/2007.10247
  • Code:https://github.com/researchmm/STTN

Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations

  • Paper:https://arxiv.org/abs/2007.06929
  • Code:https://github.com/KumapowerLIU/ECCV2020oralRethinking-Image-Inpainting-via-a-Mutual-Encoder-Decoder-with-Feature-Equalizations
  • Analysis:ECCV2020(Oral) Rethinking image inpainting

High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling

  • Paper:https://arxiv.org/abs/2005.11742v1

Short-Term and Long-Term Context Aggregation Network for Video Inpainting

Learning Object Placement by Inpainting for Compositional Data Augmentation

High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling

DVI: Depth Guided Video Inpainting for Autonomous Driving

VCNet: A Robust Approach to Blind Image Inpainting

Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes

10.图像质量评价(Image Quality Assessment)

GIQA: Generated Image Quality Assessment

PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration

持续更新~

参考

[1] ECCV 2020 超分辨率方向上接收文章总结
[2] ECCV 2020 超分辨率方向上接收文章总结(持续更新)持续更新
[3] ECCV 2020 | 空间-角度信息交互的光场图像超分辨,性能优异代码已开源
[4] ECCV2020-Code
[5] ECCV 2020 | 图匠数据、华中师范提出低质退化文本识别算法PlugNet
[6] ECCV2020(Oral) Rethinking image inpainting
[7] ECCV 2020 Oral 论文汇总!
[8] #每日五分钟一读# Image Demoireing
码字不易,如果您觉得有帮助,欢迎点赞和收藏~~

你可能感兴趣的:(图像处理与计算机视觉,论文相关,计算机视觉,深度学习,ECCV,论文合集)