A Survey of Deep Learning-Based Low-Light Image Enhancement

被引：26
作者：
Tian, Zhen [1 ,2 ]
Qu, Peixin [1 ,2 ]
Li, Jielin [1 ,2 ]
Sun, Yukun [1 ,2 ]
Li, Guohou [1 ,2 ]
Liang, Zheng [3 ]
Zhang, Weidong [1 ,2 ]
机构：
[1] Henan Inst Sci & Technol, Sch Informat Engn, Xinxiang 453003, Peoples R China
[2] Henan Inst Sci & Technol, Inst Comp Applicat, Xinxiang 453003, Peoples R China
[3] Anhui Univ, Sch Internet, Hefei 230039, Peoples R China
来源：
SENSORS | 2023年 / 23卷 / 18期
关键词：
low-light Images; image degradation; image enhancement; deep learning; QUALITY ASSESSMENT; NETWORK;
D O I：
10.3390/s23187763
中图分类号：
O65 [分析化学];
学科分类号：
070302 ; 081704 ;
摘要：
Images captured under poor lighting conditions often suffer from low brightness, low contrast, color distortion, and noise. The function of low-light image enhancement is to improve the visual effect of such images for subsequent processing. Recently, deep learning has been used more and more widely in image processing with the development of artificial intelligence technology, and we provide a comprehensive review of the field of low-light image enhancement in terms of network structure, training data, and evaluation metrics. In this paper, we systematically introduce low-light image enhancement based on deep learning in four aspects. First, we introduce the related methods of low-light image enhancement based on deep learning. We then describe the low-light image quality evaluation methods, organize the low-light image dataset, and finally compare and analyze the advantages and disadvantages of the related methods and give an outlook on the future development direction.
引用
收藏
页数：22
相关论文
共 78 条
[1]  
Aakerberg A., 2021, P 35 C NEUR INF PROC
[2]  
[Anonymous], IEEE T PATTERN ANAL, DOI DOI 10.1109/TPAMI.2021.3063604
[3]   Learning a Deep Single Image Contrast Enhancer from Multi-Exposure Images [J].
Cai, Jianrui ;
Gu, Shuhang ;
Zhang, Lei .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2018, 27 (04) :2049-2062
[4]   Learning to See in the Dark [J].
Chen, Chen ;
Chen, Qifeng ;
Xu, Jia ;
Koltun, Vladlen .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :3291-3300
[5]   Self-supervised cycle-consistent learning for scale-arbitrary real-world single image super-resolution [J].
Chen, Honggang ;
He, Xiaohai ;
Yang, Hong ;
Wu, Yuanyuan ;
Qing, Linbo ;
Sheriff, Ray E. .
EXPERT SYSTEMS WITH APPLICATIONS, 2023, 212
[6]   Deep Photo Enhancer: Unpaired Learning for Image Enhancement from Photographs with GANs [J].
Chen, Yu-Sheng ;
Wang, Yu-Ching ;
Kao, Man-Hsin ;
Chuang, Yung-Yu .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :6306-6314
[7]   CERL: A Unified Optimization Framework for Light Enhancement With Realistic Noise [J].
Chen, Zeyuan ;
Jiang, Yifan ;
Liu, Dong ;
Wang, Zhangyang .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 :4162-4172
[8]  
Fu G, 2019, IEEE IMAGE PROC, P1925, DOI 10.1109/ICIP.2019.8803197
[9]   LE-GAN: Unsupervised low-light image enhancement network using attention module and identity invariant loss [J].
Fu, Ying ;
Hong, Yang ;
Chen, Linwei ;
You, Shaodi .
KNOWLEDGE-BASED SYSTEMS, 2022, 240
[10]   Deep Bilateral Learning for Real-Time Image Enhancement [J].
Gharbi, Michael ;
Chen, Jiawen ;
Barron, Jonathan T. ;
Hasinoff, Samuel W. ;
Durand, Fredo .
ACM TRANSACTIONS ON GRAPHICS, 2017, 36 (04)
12345678