Multi-Exposure Image Fusion Through Feature Decomposition

Jong Han Kim, Kang Kyu Lee, Jong Ok Kim

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

Abstract

Multi-exposure image fusion is an effective method for fusing differently exposed low dynamic range (LDR) images to a high dynamic range (HDR) image. The previous methods suffer from poor detail and color restoration performance and visual artifact, such as halo. In this paper, to overcome these problems, we propose a novel network architecture for multi-exposure image fusion (MEF) based on feature decomposition and RGB channel fusion. A feature of LDR image is decomposed to the common and residual components at a feature level. Then, fusion is performed on the respective common and residual domain. It is found through diverse experiments that the proposed network could improve the MEF performance in aspects of color restoration and visual artifact.

Original languageEnglish
Title of host publication2021 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665408578
DOIs
Publication statusPublished - 2021
Event2021 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2021 - Gangwon, Korea, Republic of
Duration: 2021 Nov 12021 Nov 3

Publication series

Name2021 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2021

Conference

Conference2021 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2021
Country/TerritoryKorea, Republic of
CityGangwon
Period21/11/121/11/3

Keywords

  • Color restoration
  • Detail restoration
  • Feature decomposition
  • Halo artifact reduction
  • Multi-exposure image fusion

ASJC Scopus subject areas

  • Instrumentation
  • Computer Networks and Communications
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Multi-Exposure Image Fusion Through Feature Decomposition'. Together they form a unique fingerprint.

Cite this