CVPR 2020 & AAAI 2020超分辨率（super-resolution）方向上接收论文总结

CVPR 2020

官网链接：http://cvpr2020.thecvf.com/
时间：Seattle, Washington，2020年6月14日-6月19日
论文地址：http://openaccess.thecvf.com/CVPR2020.py

图像超分辨率

1. Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy

• 论文：https://arxiv.org/abs/2004.00448
• 代码：https://github.com/clovaai/cutblur
• 描述：用于超分辨率的数据增广

2. Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution

• 论文：https://arxiv.org/abs/2003.07018
• 代码：https://github.com/guoyongcs/DRN
• 描述：Dual Regression, SISR STOA

3. Light Field Spatial Super-resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization（oral）

• 论文：https://arxiv.org/abs/2004.02215

4. Structure-Preserving Super Resolution with Gradient Guidance

• 论文：https://arxiv.org/pdf/2003.13081.pdf
• 代码：https://github.com/Maclory/SPSR
• 描述：Gradient Guidance, GAN

5. Deep unfolding network for image super-resolution

• 论文：https://arxiv.org/pdf/2003.10428.pdf
• 代码：https://github.com/cszn/USRNet

6. PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

• 论文：https://arxiv.org/pdf/2003.03808.pdf

7. EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learning

• 论文：https://arxiv.org/pdf/2003.07640.pdf
• 视频：https://www.youtube.com/watch?v=OShS_MwHecs
• 数据集：https://github.com/wl082013/ESIM_dataset

8. Unified Dynamic Convolutional Network for Super-Resolution with Variational Degradations

• 论文：https://arxiv.org/abs/2004.06965
• 描述：Unified Dynamic，SISR， denoise

9. Learning Texture Transformer Network for Image Super-Resolution

• 论文：https://arxiv.org/abs/2006.04139
• 代码：https://github.com/FuzhiYang/TTSR

10. Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining

• 论文：https://arxiv.org/abs/2006.01424
• 代码：https://github.com/SHI-Labs/Cross-Scale-Non-Local-Attention

11. Unpaired Image Super-Resolution Using Pseudo-Supervision

• 论文：https://arxiv.org/abs/2002.11397

12. Correction Filter for Single Image Super-Resolution: Robustifying Off-the-Shelf Deep Super-Resolvers

• 论文：https://arxiv.org/abs/1912.00157

13. Residual Feature Aggregation Network for Image Super-Resolution
14. Robust Reference-Based Super-Resolution With Similarity-Aware Deformable Convolution

视频超分辨率

1. Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution

• 论文：https://arxiv.org/abs/2002.11616
• 代码：https://github.com/Mukosame/Zooming-Slow-Mo-CVPR-2020

2. Space-Time-Aware Multi-Resolution Video Enhancement

• 论文：http://arxiv.org/abs/2003.13170
• 代码：https://github.com/alterzero/STARnet
• 主页：https://alterzero.github.io/projects/STAR.html

3. TDAN: Temporally-Deformable Alignment Network for Video Super-Resolution

• 论文：https://arxiv.org/abs/1812.02898v1
• 代码：https://github.com/YapengTian/TDAN-VSR-CVPR-2020

4. Video Super-Resolution With Temporal Group Attention

• 代码：https://github.com/junpan19/VSR_TGA

小样本/零样本

1. Meta-Transfer Learning for Zero-Shot Super-Resolution

• 论文：https://arxiv.org/abs/2002.12213
• 代码：https://github.com/JWSoh/MZSR

人脸超分辨率

1. Learning to Have an Ear for Face Super-Resolution

• 论文：https://arxiv.org/abs/1909.12780
• 代码：https://github.com/gmeishvili/ear_for_face_super_resolution
• 网站：https://gmeishvili.github.io/ear_for_face_super_resolution/index.html

2. Deep Face Super-Resolution With Iterative Collaboration Between Attentive Recovery and Landmark Estimation

• 论文：https://arxiv.org/abs/2003.13063
• 代码：https://github.com/Maclory/Deep-Iterative-Collaboration

深度图超分辨率

1. Channel Attention Based Iterative Residual Learning for Depth Map Super-Resolution

• 论文：https://arxiv.org/abs/2006.01469

光场图像超分辨率

1. Light Field Spatial Super-Resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization

• 代码：https://github.com/jingjin25/LFSSR-ATO

高光谱图像超分辨率

1. Unsupervised Adaptation Learning for Hyperspectral Imagery Super-Resolution

• 代码：https://github.com/JiangtaoNie/UAL

超分辨率用于语义分割

1. Dual Super-Resolution Learning for Semantic Segmentation

• 代码：https://github.com/wanglixilinx/DSRL

AAAI 2020

第 34 届AAAI 2020 在 2 月 7 日-2 月 12 日于美国纽约举办。

图像超分辨率

1. Joint Super-Resolution and Alignment of Tiny Faces

• 论文：https://arxiv.org/pdf/1911.08566

2. Scale-wise Convolution for Image Restoration（名字看起来和超分辨率无关但是内容相关）

• 论文：https://arxiv.org/pdf/1912.09028.pdf

3. Image Formation Model Guided Deep Image Super-Resolution

• 论文：https://arxiv.org/abs/1908.06444
• 代码：https://github.com/jspan/PHYSICS（404？）

视频超分辨率

1. Video Face Super-Resolution with Motion-Adaptive Feedback Cell

• 论文：https://arxiv.org/pdf/2002.06378
• 代码：https://github.com/JihyongOh/FISR

2. FISR: Deep Joint Frame Interpolation and Super-Resolution with A Multi-scale Temporal Loss

• 论文：https://arxiv.org/pdf/1912.07213

3. JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video

• 论文：https://arxiv.org/pdf/1909.04391

其他值得关注的论文

1. VESR-Net: The Winning Solution to Youku Video Enhancement and Super-Resolution Challenge

• 论文：https://arxiv.org/pdf/2003.02115.pdf
• 描述：The champion of Youku-VESR challenge

2. Deep Space-Time Video Upsampling Networks

• 论文：https://arxiv.org/pdf/2004.02432.pdf
• 代码：https://github.com/JaeYeonKang/STVUN-Pytorch
• 描述：Video Super-Resolution, Video Frame Interpolation, Joint space-time upsampling

3. DeepSEE: Deep Disentangled Semantic Explorative Extreme Super-Resolution

• 论文：https://arxiv.org/pdf/2004.04433.pdf
• 代码：https://mcbuehler.github.io/DeepSEE/
• 描述：Extreme super-resolution,32× magnification

4. Unsupervised Real-world Image Super Resolution via Domain-distance Aware Training

• 论文：https://arxiv.org/pdf/2004.01178.pdf
• 代码：https://github.com/ShuhangGu/DASR（Coming soon!）
• 描述：Real-World Image Super-Resolution, Unsupervised SuperResolution, Domain Adaptation.

5. Optimizing Generative Adversarial Networks for Image Super Resolution via Latent Space Regularization

• 论文：https://arxiv.org/pdf/2001.08126.pdf
• 描述：Latent Space Regularization for srgan

6. Hierarchical Neural Architecture Search for Single Image Super-Resolution

• 论文：https://arxiv.org/pdf/2003.04619.pdf
• 代码：https://github.com/guoyongcs/HNAS-SR
• 描述：Hierarchical Neural Architecture Search, Lightweight

7. Learning for Scale-Arbitrary Super-Resolution from Scale-Specific Networks

• 论文：https://arxiv.org/pdf/2004.03791.pdf
• 描述：Scale-Arbitrary Super-Resolution, Knowledge Transfer

8. Deep Adaptive Inference Networks for Single Image Super-Resolution

• 论文：https://arxiv.org/pdf/2004.03915.pdf
• 代码：https://github.com/csmliu/AdaDSR

9. Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks

• 论文：https://arxiv.org/pdf/2003.07119.pdf
• 代码： https://github.com/sfm-sr-denoising/sfm

10. DDet: Dual-path Dynamic Enhancement Network for Real-World Image Super-Resolution

• 论文：https://arxiv.org/abs/2002.11079
• 代码：https://github.com/ykshi/DDet

11. Deep Interleaved Network for Image Super-Resolution With Asymmetric
    Co-Attention (IJCAI-PRICAI 2020)

• 论文：https://arxiv.org/abs/2004.11814
• 描述：SISR，asymmetric co-attention

12. Pyramid Attention Networks for Image Restoration

• 论文：https://arxiv.org/pdf/2004.13824.pdf
• 代码：https://github.com/SHI-Labs/Pyramid-Attention-Networks

13. Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-Resolution

• 论文：https://arxiv.org/pdf/2005.00953.pdf
• 代码：https://github.com/RaoUmer/SRResCGAN

参考资料

1. https://github.com/amusi/CVPR2020-Code
2. https://github.com/extreme-assistant/CVPR2020-Paper-Code-Interpretation/blob/master/CVPR2020.md
3. https://github.com/ChaofWang/Awesome-Super-Resolution
4. https://paperswithcode.com/task/image-super-resolution/
5. CVPR 2020 论文大盘点-超分辨率篇