Adversarial Context Aggregation Network for Low-Light Image Enhancement

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

doi:10.1109/DICTA.2018.8615848

Adversarial Context Aggregation Network for Low-Light Image Enhancement

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

School of Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 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 language	English
Title of host publication	2018 International Conference on Digital Image Computing
Subtitle of host publication	Techniques and Applications, DICTA 2018
Editors	Mark Pickering, Lihong Zheng, Shaodi You, Ashfaqur Rahman, Manzur Murshed, Md Asikuzzaman, Ambarish Natu, Antonio Robles-Kelly, Manoranjan Paul
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781538666029
DOIs	https://doi.org/10.1109/DICTA.2018.8615848
Publication status	Published - 2019 Jan 16
Event	2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018 - Canberra, Australia Duration: 2018 Dec 10 → 2018 Dec 13

Publication series

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

Conference

Conference	2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018
Country/Territory	Australia
City	Canberra
Period	18/12/10 → 18/12/13

Bibliographical note

Funding Information:
1This work was supported by Institute for Information & communications Technology Promotion(IITP) grant funded by the Korea government(MSIT) (2017-0-00250, Intelligent Defense Boundary Surveillance Technology Using Collaborative Reinforced Learning of Embedded Edge Camera and Image Analysis).

Publisher Copyright:
© 2018 IEEE.

Keywords

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

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

Access to Document

10.1109/DICTA.2018.8615848

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 Article 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

Adversarial Context Aggregation Network for Low-Light Image Enhancement. / Shin, Yong Goo; Sagong, Min Cheol; Yeo, Yoon Jae et al.
2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018. ed. / Mark Pickering; Lihong Zheng; Shaodi You; Ashfaqur Rahman; Manzur Murshed; Md Asikuzzaman; Ambarish Natu; Antonio Robles-Kelly; Manoranjan Paul. Institute of Electrical and Electronics Engineers Inc., 2019. 8615848 (2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Shin, YG, Sagong, MC, Yeo, YJ & Ko, SJ 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., 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018, Canberra, Australia, 18/12/10. https://doi.org/10.1109/DICTA.2018.8615848

Shin YG, Sagong MC, Yeo YJ, Ko SJ. Adversarial Context Aggregation Network for Low-Light Image Enhancement. In Pickering M, Zheng L, You S, Rahman A, Murshed M, Asikuzzaman M, Natu A, Robles-Kelly A, Paul M, editors, 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018. Institute of Electrical and Electronics Engineers Inc. 2019. 8615848. (2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018). doi: 10.1109/DICTA.2018.8615848

Shin, Yong Goo ; Sagong, Min Cheol ; Yeo, Yoon Jae et al. / Adversarial Context Aggregation Network for Low-Light Image Enhancement. 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018. editor / Mark Pickering ; Lihong Zheng ; Shaodi You ; Ashfaqur Rahman ; Manzur Murshed ; Md Asikuzzaman ; Ambarish Natu ; Antonio Robles-Kelly ; Manoranjan Paul. Institute of Electrical and Electronics Engineers Inc., 2019. (2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018).

@inproceedings{989b0c85588b4d848e7e6ce1b18ccf1b,

title = "Adversarial Context Aggregation Network for Low-Light Image Enhancement",

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 ",

keywords = "Convolutional neural network, Low-light image enhancement, context aggregation, generative adversarial network",

author = "Shin, {Yong Goo} and Sagong, {Min Cheol} and Yeo, {Yoon Jae} and Ko, {Sung Jea}",

note = "Funding Information: 1This work was supported by Institute for Information & communications Technology Promotion(IITP) grant funded by the Korea government(MSIT) (2017-0-00250, Intelligent Defense Boundary Surveillance Technology Using Collaborative Reinforced Learning of Embedded Edge Camera and Image Analysis). Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018 ; Conference date: 10-12-2018 Through 13-12-2018",

year = "2019",

month = jan,

day = "16",

doi = "10.1109/DICTA.2018.8615848",

language = "English",

series = "2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Mark Pickering and Lihong Zheng and Shaodi You and Ashfaqur Rahman and Manzur Murshed and Md Asikuzzaman and Ambarish Natu and Antonio Robles-Kelly and Manoranjan Paul",

booktitle = "2018 International Conference on Digital Image Computing",

}

TY - GEN

T1 - Adversarial Context Aggregation Network for Low-Light Image Enhancement

AU - Shin, Yong Goo

AU - Sagong, Min Cheol

AU - Yeo, Yoon Jae

AU - Ko, Sung Jea

N1 - Funding Information: 1This work was supported by Institute for Information & communications Technology Promotion(IITP) grant funded by the Korea government(MSIT) (2017-0-00250, Intelligent Defense Boundary Surveillance Technology Using Collaborative Reinforced Learning of Embedded Edge Camera and Image Analysis). Publisher Copyright: © 2018 IEEE.

PY - 2019/1/16

Y1 - 2019/1/16

N2 - 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

AB - 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

KW - Convolutional neural network

KW - Low-light image enhancement

KW - context aggregation

KW - generative adversarial network

UR - http://www.scopus.com/inward/record.url?scp=85062233253&partnerID=8YFLogxK

U2 - 10.1109/DICTA.2018.8615848

DO - 10.1109/DICTA.2018.8615848

M3 - Conference contribution

AN - SCOPUS:85062233253

T3 - 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018

BT - 2018 International Conference on Digital Image Computing

A2 - Pickering, Mark

A2 - Zheng, Lihong

A2 - You, Shaodi

A2 - Rahman, Ashfaqur

A2 - Murshed, Manzur

A2 - Asikuzzaman, Md

A2 - Natu, Ambarish

A2 - Robles-Kelly, Antonio

A2 - Paul, Manoranjan

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018

Y2 - 10 December 2018 through 13 December 2018

ER -

Adversarial Context Aggregation Network for Low-Light Image Enhancement

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this