Kindling the Darkness: A Practical Low-light Image Enhancer

被引:799
作者
Zhang, Yonghua [1 ]
Zhang, Jiawan [1 ]
Guo, Xiaojie [1 ]
机构
[1] Tianjin Univ, Coll Intelligence & Comp, Tianjin, Peoples R China
来源
PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19) | 2019年
基金
中国国家自然科学基金;
关键词
low light enhancement; image decomposition; image restoration; HISTOGRAM EQUALIZATION; RETINEX;
D O I
10.1145/3343031.3350926
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Images captured under low-light conditions often suffer from (partially) poor visibility. Besides unsatisfactory lightings, multiple types of degradations, such as noise and color distortion due to the limited quality of cameras, hide in the dark. In other words, solely turning up the brightness of dark regions will inevitably amplify hidden artifacts. This work builds a simple yet effective network for Kindling the Darkness (denoted as KinD), which, inspired by Retinex theory, decomposes images into two components. One component (illumination) is responsible for light adjustment, while the other (reflectance) for degradation removal. In such a way, the original space is decoupled into two smaller subspaces, expecting to be better regularized/learned. It is worth to note that our network is trained with paired images shot under different exposure conditions, instead of using any ground-truth reflectance and illumination information. Extensive experiments are conducted to demonstrate the efficacy of our design and its superiority over state-of-the-art alternatives. Our KinD is robust against severe visual defects, and user-friendly to arbitrarily adjust light levels. In addition, our model spends less than 50ms to process an image in VGA resolution on a 2080Ti GPU. All the above merits make our KinD attractive for practical use.
引用
收藏
页码:1632 / 1640
页数:9
相关论文
共 34 条
[1]   A dynamic histogram equalization for image contrast enhancement [J].
Abdullah-Al-Wadud, M. ;
Kabir, Md. Hasanul ;
Dewan, M. Ali Akber ;
Chae, Oksam .
IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2007, 53 (02) :593-600
[2]  
Agostinelli F., 2013, Adv. Neural Inf. Process. Syst, P1493
[3]  
[Anonymous], 2018, BRIT MACH VIS C BRIT
[4]   DehazeNet: An End-to-End System for Single Image Haze Removal [J].
Cai, Bolun ;
Xu, Xiangmin ;
Jia, Kui ;
Qing, Chunmei ;
Tao, Dacheng .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2016, 25 (11) :5187-5198
[5]   Contextual and Variational Contrast Enhancement [J].
Celik, Turgay ;
Tjahjadi, Tardi .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2011, 20 (12) :3431-3441
[6]   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
[7]   Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration [J].
Chen, Yunjin ;
Pock, Thomas .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (06) :1256-1272
[8]   A simple and effective histogram equalization approach to image enhancement [J].
Cheng, HD ;
Shi, XJ .
DIGITAL SIGNAL PROCESSING, 2004, 14 (02) :158-170
[9]   Image denoising by sparse 3-D transform-domain collaborative filtering [J].
Dabov, Kostadin ;
Foi, Alessandro ;
Katkovnik, Vladimir ;
Egiazarian, Karen .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2007, 16 (08) :2080-2095
[10]   Compression Artifacts Reduction by a Deep Convolutional Network [J].
Dong, Chao ;
Deng, Yubin ;
Loy, Chen Change ;
Tang, Xiaoou .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :576-584