TechRxiv
Synchronous Rain Streaks and Raindrops Removal_TechRxiv.pdf (12.2 MB)
Download file

Robust Attention Deraining Network for Synchronous Rain Streaks and Raindrops Removal

Download (12.2 MB)
preprint
posted on 17.05.2022, 03:11 authored by Yanyan Wei, Zhao ZhangZhao Zhang, Mingliang Xu, Richang Hong, Jicong Fan, Shuicheng Yan

Synchronous Rain streaks and Raindrops Removal (SR$^3$) is a hard and challenging task, since rain streaks and raindrops are two wildly divergent real-world phenomena with different optical properties and mathematical distributions. As such, most of existing data-driven deep singe image deraining (SID) methods only focus on one of them. Although there are only a few existing SR$^3$ methods, they still suffer from blur textures and unknown noise in reality due to weak robustness and generalization ability. In this paper,  we will propose a new and universal SID model with novel modules, termed Robust Attention Deraining Network (RadNet), with strong robustness and generalization ability that are reflected in two main aspects. (1) RadNet can restore different rain degenerations, including raindrops, rain streaks, or both; (2) RadNet can adapt to different data strategies, including single-type, superimposed-type, and blended-type. The generalization ability is also demonstrated by the performance of dealing with real rainy images. Specifically, we first design a lightweight and robust attention module (RAM) with a universal attention mechanism for coarse rain removal, and then present a new deep refining module (DRM) with multi-scales blocks for precise rain removal. To solve the inconsistent labels of real scenario data, we also introduce a flow \& warp module (FWM) into the network, which can greatly improve the performance on real scenario data via optical flow prediction and alignment. The whole process is unified in a network to ensure sufficient robustness and strong generalization ability. We evaluated the performance of our method under a variety of data strategies, and extensive experiments demonstrated that our RadNet can outperform other state-of-the-art SID methods. 

History

Email Address of Submitting Author

cszzhang@gmail.com

Submitting Author's Institution

Hefei University of Technology

Submitting Author's Country

China