Semi-DRDNet Semi-supervised Detail-recovery Image Deraining Network via Unpaired Contrastive Learning

Yiyang Shen, Sen Deng, Wenhan Yang, Mingqiang Wei, Haoran Xie, Xiaoping Zhang, Jing Qin, Meng Wang

Abstract

The intricacy of rainy image contents often leads cutting-edge deraining models to image degradation including remnant rain, wrongly-removed details, and distorted appearance. Such degradation is further exacerbated when applying the models trained on synthetic data to real-world rainy images. We raise an intriguing question -- if leveraging both accessible unpaired clean/rainy yet real-world images and additional detail repair guidance, can improve the generalization ability of a deraining model? To answer it, we propose a semi-supervised detail-recovery image deraining network (termed as Semi-DRDNet). Semi-DRDNet consists of three branches: 1) for removing rain streaks without remnants, we present a \textit{squeeze-and-excitation} (SE)-based rain residual network; 2) for encouraging the lost details to return, we construct a \textit{structure detail context aggregation} (SDCAB)-based detail repair network; to our knowledge, this is the first time; and 3) for bridging the domain gap, we develop a novel contrastive regularization network to learn from unpaired positive (clean) and negative (rainy) yet real-world images. As a semi-supervised learning paradigm, Semi-DRDNet operates smoothly on both synthetic and real-world rainy data in terms of deraining robustness and detail accuracy. Comparisons on four datasets show clear visual and numerical improvements of our Semi-DRDNet over thirteen state-of-the-arts.
BibTeX
@misc{shen2022semi,
  author = {Yiyang Shen and Sen Deng and Wenhan Yang and Mingqiang Wei and Haoran Xie and Xiaoping Zhang and Jing Qin and Meng Wang},
  title = {{Semi-DRDNet Semi-supervised Detail-recovery Image Deraining Network via Unpaired Contrastive Learning}},
  year = {2022},
  eprint = {2204.02772},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2204.02772},
}
Figure