SEMI-DERAINGAN: A NEW SEMI-SUPERVISED SINGLE IMAGE DERAINING

Yanyan Wei, Zhao Zhang*, Yang Wang, Haijun Zhang, Mingbo Zhao, Mingliang Xu*, Meng Wang

*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

37 Citations (Scopus)

Abstract

Although supervised single image deraining (SID) have obtained impressive results, they still cannot obtain satisfactory results on real images for the weak generalization of rain removal capacity. In this paper, we mainly discuss the semi-supervised SID and propose a new GAN-based deraining network called Semi-DerainGAN, which can use both synthetic and real data in a uniform network based on two supervised and unsupervised processes. For this task, a semi-supervised rain streak learner termed SSRML sharing the same parameters of both processes is derived, which makes the real images contribute more rain streak information, so that the resulted model has a strong generalization power to the real SID task. We also contribute a new real-world rain image dataset called Real200 to alleviate the difference between both synthetic and real image domains. Extensive results on public datasets show that our model can obtain competitive results, especially on the real rain images.
Original languageEnglish
Title of host publication2021 IEEE International Conference on Multimedia and Expo (ICME)
PublisherIEEE
ISBN (Electronic)978-1-6654-3864-3
DOIs
Publication statusPublished - Jul 2021
Event2021 IEEE International Conference on Multimedia and Expo, ICME 2021 - Shenzhen, China
Duration: 5 Jul 20219 Jul 2021

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Conference

Conference2021 IEEE International Conference on Multimedia and Expo, ICME 2021
Country/TerritoryChina
CityShenzhen
Period5/07/219/07/21

Research Keywords

  • dataset
  • rain removal
  • Semi-supervised learning
  • Single image deraining

Fingerprint

Dive into the research topics of 'SEMI-DERAINGAN: A NEW SEMI-SUPERVISED SINGLE IMAGE DERAINING'. Together they form a unique fingerprint.

Cite this