Single Image De-Raining with High-Low Frequency Guidance

Ying Zhang, Youjun Xiang, Lei Cai, Yuli Fu, Wanliang Huo, Junjun XiaICASSP 2022 · DOI

Abstract

Rain removal is a highly demanding task because a rainy image in computer lacks discriminative information to distinguish the image details from the rain streaks. In this paper, we present a new High-Low-Frequency Guided De-raining (HLFGD) method to remove the rain streaks clearly while reserve the image details. Specifically, the proposed HLFGD is built with three network branches, namely global-structure branch, de-raining branch, and edge-detail branch, which achieve the collaboration by concatenating intermediate features. Among them, the global-structure and edge-detail branches aim to explore the high-low frequency information, and the de-raining branch leverages the resulting spatial frequency information to restore the global structure of image and to retain fine edge details of objects during the de-raining process. Besides, a new architecture unit, called Residual Co-ordinate Attention Block (RCAB), is proposed to improve the effect of rain removal. Experimental results show the superiority of our method for image de-raining quantificationally and qualitatively.
BibTeX
@inproceedings{zhang2022single,
  author = {Ying Zhang and Youjun Xiang and Lei Cai and Yuli Fu and Wanliang Huo and Junjun Xia},
  title = {{Single Image De-Raining with High-Low Frequency Guidance}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2022},
  doi = {10.1109/icassp43922.2022.9747812},
}

Loading related content...

Figure