MBA-RainGAN: A Multi-Branch Attention Generative Adversarial Network for Mixture of Rain Removal
Yiyang Shen, Yidan Feng, Weiming Wang, Dong Liang, Jing Qin, Haoran Xie, Mingqiang Wei
Abstract
Rain severely degrades the visibility of scene objects, especially when images are captured through the glass under rainy weather. We observe three intriguing phenomena: 1) rain is a mixture of raindrops, rain streaks and rainy haze; 2) the depth from the camera determines the degree of object visibility, where objects nearby and far away are visually blocked by rain streaks and rainy haze, respectively; and 3) raindrops on the glass randomly affect the object visibility of the whole image space. However, existing solutions and benchmark datasets lack full consideration of the mixture of rain (MOR). In this paper, we originally consider that the overall object visibility is determined by MOR, and enrich the RainCityscapes by considering real-world raindrops to construct the MOR dataset, named RainCityscapes++. To solve the practical rain removal problem arisen from MOR, we formulate a new rain imaging model and propose a multi-branch attention generative adversarial network (MBA-RainGAN). Extensive experiments show clear improvements of our approach over SOTAs on RainCityscapes++.
BibTeX
@inproceedings{icassp2022_mbarainganamulti,
title = {MBA-RainGAN: A Multi-Branch Attention Generative Adversarial Network for Mixture of Rain Removal},
author = {Yiyang Shen and Yidan Feng and Weiming Wang and Dong Liang and Jing Qin and Haoran Xie and Mingqiang Wei},
booktitle = {ICASSP 2022},
year = {2022}
}