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 -