Adversarial Context Aggregation Network for Low-Light Image Enhancement

Yong Goo Shin, Min Cheol Sagong, Yoon Jae Yeo, Sung-Jea Ko

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

2 Citations (Scopus)

Abstract

Image captured in the low-light environments usually suffers from the low dynamic ranges and noise which degrade the quality of the image. Recently, convolutional neural network (CNN) has been employed for low-light image enhancement to simultaneously perform the brightness enhancement and noise removal. Although conventional CNN based techniques exhibit superior performance compared to traditional non-CNN based methods, they often produce the image with visual artifacts due to the small receptive field in their network. In order to cope with this problem, we propose an adversarial context aggregation network (ACA-net) for low-light image enhancement, which effectively aggregates the global context via full-resolution intermediate layers. In the proposed method, we first increase the brightness of a low-light image using the two different gamma correction functions and then feed the brightened images to CNN to obtain the enhanced image. To this end, we train ACA network using L1 pixel-wise reconstruction loss and adversarial loss which encourages the network to generate a natural image. Experimental results show that the proposed method achieves state-of-the-art results in terms of peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). 1

Original languageEnglish
Title of host publication2018 International Conference on Digital Image Computing
Subtitle of host publicationTechniques and Applications, DICTA 2018
EditorsMark Pickering, Lihong Zheng, Shaodi You, Ashfaqur Rahman, Manzur Murshed, Md Asikuzzaman, Ambarish Natu, Antonio Robles-Kelly, Manoranjan Paul
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538666029
DOIs
Publication statusPublished - 2019 Jan 16
Event2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018 - Canberra, Australia
Duration: 2018 Dec 102018 Dec 13

Publication series

Name2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018

Conference

Conference2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018
CountryAustralia
CityCanberra
Period18/12/1018/12/13

Keywords

  • context aggregation
  • Convolutional neural network
  • generative adversarial network
  • Low-light image enhancement

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Health Informatics
  • Radiology Nuclear Medicine and imaging

Fingerprint Dive into the research topics of 'Adversarial Context Aggregation Network for Low-Light Image Enhancement'. Together they form a unique fingerprint.

  • Cite this

    Shin, Y. G., Sagong, M. C., Yeo, Y. J., & Ko, S-J. (2019). Adversarial Context Aggregation Network for Low-Light Image Enhancement. In M. Pickering, L. Zheng, S. You, A. Rahman, M. Murshed, M. Asikuzzaman, A. Natu, A. Robles-Kelly, & M. Paul (Eds.), 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018 [8615848] (2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DICTA.2018.8615848