Unsupervised Decomposition and Correction Network for Low-Light Image Enhancement

Qiuping JIANG, Yudong MAO, Runmin CONG, Wenqi REN, Chao HUANG*, Feng SHAO

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

51 Citations (Scopus)

Abstract

Vision-based intelligent driving assistance systems and transportation systems can be improved by enhancing the visibility of the scenes captured in extremely challenging conditions. In particular, many low-image image enhancement (LIE) algorithms have been proposed to facilitate such applications in low-light conditions. While deep learning-based methods have achieved substantial success in this field, most of them require paired training data, which is difficult to be collected. This paper advocates a novel Unsupervised Decomposition and Correction Network (UDCN) for LIE without depending on paired data for training. Inspired by the Retinex model, our method first decomposes images into illumination and reflectance components with an image decomposition network (IDN). Then, the decomposed illumination is processed by an illumination correction network (ICN) and fused with the reflectance to generate a primary enhanced result. In contrast with fully supervised learning approaches, UDCN is an unsupervised one which is trained only with low-light images and corresponding histogram equalized (HE) counterparts (can be derived from the low-light image itself) as input. Both the decomposition and correction networks are optimized under the guidance of hybrid no-reference quality-aware losses and inter-consistency constraints between the low-light image and its HE counterpart. In addition, we also utilize an unsupervised noise removal network (NRN) to remove the noise previously hidden in the darkness for further improving the primary result. Qualitative and quantitative comparison results are reported to demonstrate the efficacy of UDCN and its superiority over several representative alternatives in the literature. The results and code will be made public available at https://github.com/myd945/UDCN.

Original languageEnglish
Pages (from-to)19440-19455
Number of pages16
JournalIEEE Transactions on Intelligent Transportation Systems
Volume23
Issue number10
Early online date14 Apr 2022
DOIs
Publication statusPublished - Oct 2022
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2000-2011 IEEE.

Keywords

  • deep learning
  • image enhancement
  • Low-light image
  • Retinex model
  • unsupervised learning

Fingerprint

Dive into the research topics of 'Unsupervised Decomposition and Correction Network for Low-Light Image Enhancement'. Together they form a unique fingerprint.

Cite this