Row-Column Separated Attention Based Low-Light Image/Video Enhancement

doi:10.1111/cgf.15192

	Row-Column Separated Attention Based Low-Light Image/Video Enhancement
	Dong, Chengqi 1; Cao, Zhiyuan 2; Qi, Tuoshi 1; Wu, Kexin 1; Gao, Yixing 1; Tang, Fan 3
	2024-08-29
发表期刊	COMPUTER GRAPHICS FORUM
ISSN	0167-7055
页码	15
摘要	U-Net structure is widely used for low-light image/video enhancement. The enhanced images result in areas with large local noise and loss of more details without proper guidance for global information. Attention mechanisms can better focus on and use global information. However, attention to images could significantly increase the number of parameters and computations. We propose a Row-Column Separated Attention module (RCSA) inserted after an improved U-Net. The RCSA module's input is the mean and maximum of the row and column of the feature map, which utilizes global information to guide local information with fewer parameters. We propose two temporal loss functions to apply the method to low-light video enhancement and maintain temporal consistency. Extensive experiments on the LOL, MIT Adobe FiveK image, and SDSD video datasets demonstrate the effectiveness of our approach. We design a row-column separation attention model for high-quality low light enhancement. image
关键词	Low-light image/video enhancement Row-column separated attention Temporal consistency
DOI	10.1111/cgf.15192
收录类别	SCI
语种	英语
资助项目	Beijing Natural Science Foundation[L221013] ; National Natural Science Foundation of China[62102162] ; National Natural Science Foundation of China[62203184]
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:001300036700001
出版者	WILEY
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/39614
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Gao, Yixing
作者单位	1.Jilin Univ, Sch Artificial Intelligence, Changchun, Peoples R China 2.Jilin Univ, Coll Software, Changchun, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Dong, Chengqi,Cao, Zhiyuan,Qi, Tuoshi,et al. Row-Column Separated Attention Based Low-Light Image/Video Enhancement[J]. COMPUTER GRAPHICS FORUM,2024:15.
APA	Dong, Chengqi,Cao, Zhiyuan,Qi, Tuoshi,Wu, Kexin,Gao, Yixing,&Tang, Fan.(2024).Row-Column Separated Attention Based Low-Light Image/Video Enhancement.COMPUTER GRAPHICS FORUM,15.
MLA	Dong, Chengqi,et al."Row-Column Separated Attention Based Low-Light Image/Video Enhancement".COMPUTER GRAPHICS FORUM (2024):15.