Low-Light Image Enhancement via a Deep Hybrid Network

doi:10.1109/TIP.2019.2910412

	Low-Light Image Enhancement via a Deep Hybrid Network
	Ren, Wenqi 1; Liu, Sifei 2; Ma, Lin 3; Xu, Qianqian 4; Xu, Xiangyu 5; Cao, Xiaochun 1; Du, Junping 6; Yang, Ming-Hsuan 7
	2019-09-01
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	28 期号:9 页码:4364-4375
摘要	Camera sensors often fail to capture clear images or videos in a poorly lit environment. In this paper, we propose a trainable hybrid network to enhance the visibility of such degraded images. The proposed network consists of two distinct streams to simultaneously learn the global content and the salient structures of the clear image in a unified network. More specifically, the content stream estimates the global content of the low-light input through an encoder-decoder network. However, the encoder in the content stream tends to lose some structure details. To remedy this, we propose a novel spatially variant recurrent neural network (RNN) as an edge stream to model edge details, with the guidance of another auto-encoder. The experimental results show that the proposed network favorably performs against the state-of-the-art low-light image enhancement algorithms.
关键词	Low-light image enhancement convolutional neural network recurrent neural network
DOI	10.1109/TIP.2019.2910412
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[U1736219] ; National Natural Science Foundation of China[U1605252] ; National Natural Science Foundation of China[U1803264] ; National Natural Science Foundation of China[61532006] ; National Natural Science Foundation of China[61772083] ; National Natural Science Foundation of China[61802403] ; National Key R&D Program of China[2018YFB0803701] ; Beijing Natural Science Foundation[L182057] ; CCF-Tencent Open Fund
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000473641100014
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：330[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/4316
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Cao, Xiaochun
作者单位	1.Chinese Acad Sci, Inst Informat Engn, State Key Lab Informat Secur, Beijing 100093, Peoples R China 2.NVIDIA Res, Santa Clara, CA 95051 USA 3.Tencent AI Lab, Shenzhen 518000, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100080, Peoples R China 5.SenseTime, Beijing 100084, Peoples R China 6.Beijing Univ Posts & Telecommun, Sch Comp Sci, Beijing 100876, Peoples R China 7.Univ Calif Merced, Sch Engn, Merced, CA 95343 USA
推荐引用方式 GB/T 7714	Ren, Wenqi,Liu, Sifei,Ma, Lin,et al. Low-Light Image Enhancement via a Deep Hybrid Network[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2019,28(9):4364-4375.
APA	Ren, Wenqi.,Liu, Sifei.,Ma, Lin.,Xu, Qianqian.,Xu, Xiangyu.,...&Yang, Ming-Hsuan.(2019).Low-Light Image Enhancement via a Deep Hybrid Network.IEEE TRANSACTIONS ON IMAGE PROCESSING,28(9),4364-4375.
MLA	Ren, Wenqi,et al."Low-Light Image Enhancement via a Deep Hybrid Network".IEEE TRANSACTIONS ON IMAGE PROCESSING 28.9(2019):4364-4375.