Cycle-interactive generative adversarial network for robust unsupervised low-light enhancement

Zhangkai NI, Wenhan YANG, Hanli WANG, Shiqi WANG, Lin MA, Sam KWONG

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

8 Citations (Scopus)

Abstract

Getting rid of the fundamental limitations in fitting to the paired training data, recent unsupervised low-light enhancement methods excel in adjusting illumination and contrast of images. However, for unsupervised low light enhancement, the remaining noise suppression issue due to the lacking of supervision of detailed signal largely impedes the wide deployment of these methods in real-world applications. Herein, we propose a novel Cycle-Interactive Generative Adversarial Network (CIGAN) for unsupervised low-light image enhancement, which is capable of not only better transferring illumination distributions between low/normal-light images but also manipulating detailed signals between two domains, e.g., suppressing/synthesizing realistic noise in the cyclic enhancement/degradation process. In particular, the proposed low-light guided transformation feed-forwards the features of low-light images from the generator of enhancement GAN (eGAN) into the generator of degradation GAN (dGAN). With the learned information of real low-light images, dGAN can synthesize more realistic diverse illumination and contrast in low-light images. Moreover, the feature randomized perturbation module in dGAN learns to increase the feature randomness to produce diverse feature distributions, persuading the synthesized low-light images to contain realistic noise. Extensive experiments demonstrate both the superiority of the proposed method and the effectiveness of each module in CIGAN.
Original languageEnglish
Title of host publicationProceedings of the 30th ACM International Conference on Multimedia
PublisherAssociation for Computing Machinery (ACM)
Pages1484-1492
Number of pages9
ISBN (Print)9781450392037
DOIs
Publication statusPublished - 10 Oct 2022
Externally publishedYes
EventThe 30th ACM International Conference on Multimedia - Lisbon, Portugal
Duration: 10 Oct 202214 Oct 2022

Conference

ConferenceThe 30th ACM International Conference on Multimedia
Country/TerritoryPortugal
CityLisbon
Period10/10/2214/10/22

Bibliographical note

This work was supported in part by National Natural Science Foundation of China under Grant 61976159, Shanghai Innovation Action Project of Science and Technology under Grant 20511100700.

Keywords

  • generative adversarial network (GAN)
  • low-light image enhancement
  • quality attention module

Fingerprint

Dive into the research topics of 'Cycle-interactive generative adversarial network for robust unsupervised low-light enhancement'. Together they form a unique fingerprint.

Cite this