ECCV 2022

除了著名的CVPR、ICCV，ECCV（欧洲计算机视觉国际会议）也是计算机视觉三大国际顶级会议之一，每两年召开一次。本届 ECCV 2022 将在10月23日-27日的以色列特拉维夫（Tel-Aviv）举行，采取线下和线上混合形式召开^[1]。而本届会议论文录用率不足20%。

现将超分辨率方向上接收的论文汇总如下，遗漏之处还请大家斧正。

图像超分

1. CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution

• Paper: https://arxiv.org/abs/2207.10345
• Code: https://github.com/Cheeun/CADyQ
• Keywords: Quantization

2. Image Super-Resolution with Deep Dictionary

• Paper: https://arxiv.org/abs/2207.09228
• Code:
• Keywords: Dictionary

3. Adaptive Patch Exiting for Scalable Single Image Super-Resolution

• Paper: https://arxiv.org/abs/2203.11589
• Code: https://github.com/littlepure2333/APE
• Keywords: Scalable

4. ARM: Any-Time Super-Resolution Method

• Paper: https://arxiv.org/abs/2203.10812
• Code: https://github.com/chenbong/ARM-Net
• Keywords: Over-parameterized

5. Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks

• Paper: https://arxiv.org/abs/2203.03844
• Code: https://github.com/zysxmu/DDTB
• Keywords: Quantization
• Blog: 基于动态对偶可训边界的低精度超分网络

6. Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution

• Paper: https://arxiv.org/abs/2207.12987
• Code: https://github.com/zhjy2016/SPLUT
• Keywords: Efficient

视频超分

1. Towards Interpretable Video Super-Resolution via Alternating Optimization

• Paper: https://arxiv.org/abs/2207.10765
• Code:
• Keywords: Interpretable

特殊场景

1. Reference-based Image Super-Resolution with Deformable Attention Transformer

• Paper: https://arxiv.org/abs/2207.11938
• Code:
• Keywords: Transformer, Reference-based (RefSR)

2. Learning Mutual Modulation for Self-Supervised Cross-Modal Super-Resolution

• Paper: https://arxiv.org/abs/2207.09156
• Code:
• Keywords: Self-Supervised, Cross-Modal

3. BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks

• Paper: https://arxiv.org/abs/2207.06873
• Code: https://github.com/ExplainableML/BayesCap
• Keywords: Uncertainty

4. Learning Local Implicit Fourier Representation for Image Warping

• Paper: https://arxiv.org/abs/2207.01831 or https://ipl.dgist.ac.kr/LTEW.pdf
• Code:
• Keywords: Image Warping

5. Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations

• Paper: https://arxiv.org/abs/2203.01325
• Code: https://github.com/cszhilu1998/SelfDZSR
• Keywords: Self-Supervised, Real-World

6. Boosting Event Stream Super-Resolution with a Recurrent Neural Network ^[2]

• Paper:
• Code:
• Keywords: Event stream

7. Deep Semantic Statistics Matching (D2SM) Denoising Network

• Paper: https://arxiv.org/abs/2207.09302
• Code:
• Keywords: Denoising

参考资料

1. ECCV 2022放榜了！1629篇论文中选，录用率不到20% ↩

2. http://staff.ustc.edu.cn/~zwxiong/ ↩