Single Low-Light Image Enhancement by Fusing Multiple Sources

Zhuang Feng, Zhiyuan Zhou, Richang Hong, Shijie Hao, Yong Ge, Meng Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

The visual quality of photographs can be seriously affected by various low-light conditions. The image enhancement methods based on fusion achieve satisfying results. However, this poses challenges to the situation that there are no fusion sources and only a single low-light image is at hand. In this paper, we propose a single low-light enhancement method by fusing multiple sources, including the original image and its intermediate enhancements generated by a simplified Retinex model. We combine these sources at a mid-level image representation based on a patch-based decomposition model. Compared with other state-of-the-art methods, visual and quantitative results show that our method effectively improves visual effects in terms of lightness, color harmony and vividness.

Original languageEnglish (US)
Title of host publication2018 IEEE 4th International Conference on Multimedia Big Data, BigMM 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538653210
DOIs
StatePublished - Oct 18 2018
Externally publishedYes
Event4th IEEE International Conference on Multimedia Big Data, BigMM 2018 - Xi'an, China
Duration: Sep 13 2018Sep 16 2018

Publication series

Name2018 IEEE 4th International Conference on Multimedia Big Data, BigMM 2018

Conference

Conference4th IEEE International Conference on Multimedia Big Data, BigMM 2018
Country/TerritoryChina
CityXi'an
Period9/13/189/16/18

Keywords

  • Fusion
  • Image Enhancement
  • Low-light Image
  • Patch Decomposition

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Information Systems and Management
  • Media Technology

Fingerprint

Dive into the research topics of 'Single Low-Light Image Enhancement by Fusing Multiple Sources'. Together they form a unique fingerprint.

Cite this