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

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

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++.
Original languageEnglish
Title of host publicationICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublisherIEEE
Pages3418-3422
DOIs
Publication statusPublished - 23 May 2022
EventICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Singapore, Singapore
Duration: 23 May 202227 May 2022

Conference

ConferenceICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Period23/05/2227/05/22

Bibliographical note

This work was supported by the National Natural Science Foundation of China (No. 62172218) and the HKMU 2020/2021 S&T School Research Fund (R5091), and the Direct Grant (DR22A2) and the Faculty Research Grants (DB22A5 and DB21A9) of Lingnan University, Hong Kong.

Keywords

  • MBA-RainGAN
  • Image deraining
  • Bidirectional coordinate attention
  • Mixture of rain
  • GAN

Fingerprint

Dive into the research topics of 'MBA-RainGAN: A Multi-Branch Attention Generative Adversarial Network for Mixture of Rain Removal'. Together they form a unique fingerprint.

Cite this