Illumination Guided Attentive Wavelet Network for Low-Light Image Enhancement

doi:10.1109/TMM.2022.3207330

	Illumination Guided Attentive Wavelet Network for Low-Light Image Enhancement
	Xu, Jingzhao 1; Yuan, Mengke2,3 ; Yan, Dong-Ming2,3 ; Wu, Tieru 1
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
	2023
卷号	25 页码:6258-6271
通讯作者	Yuan, Mengke(mengke.yuan@nlpr.ia.ac.cn) ; Wu, Tieru(wutr@jlu.edu.cn)
摘要	Deep convolutional neural networks have recently been applied to improve the quality of low-light images and have achieved promising results. However, most existing methods cannot suppress noise during the enhancement process effectively, resulting in unknown artifacts and color distortions. In addition, these methods do not fully utilize illumination information and perform poorly under extremely low-light condition. To alleviate these problems, we propose the illumination guided attentive wavelet network (IGAWN) for low-light image enhancement (LLIE). Considering that the wavelet transform can separate high-frequency noise and desired low-frequency content effectively, we enhance low-light images in the frequency domain. By integrating attention mechanisms with wavelet transform, we develop the attentive wavelet transform to capture more important wavelet features, which enables the desired content to be enhanced and the redundant noise to be suppressed. To improve the image enhancement performance under extremely low-light environment, we extract illumination information from the input images and exploit it as the guidance for image enhancement through the frequency feature transform(FFT) layer. The proposed FFT layer generates frequency-aware affine transformation from the estimated illumination information, which can adaptively modulate the image features of different frequencies. Extensive experiments on synthetic and real-world datasets demonstrate that our IGAWNperforms favorably against state-of-the-art LLIE methods.
关键词	Lighting Wavelet transforms Image enhancement Frequency modulation Wavelet coefficients Noise reduction Discrete wavelet transforms Attention mechanism illumination guidance low-light image enhancement wavelet transform
DOI	10.1109/TMM.2022.3207330
关键词[WOS]	HISTOGRAM EQUALIZATION ; QUALITY ASSESSMENT ; RETINEX
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2020YFA0714101] ; National Nature Science Foundation of China[61872162] ; National Nature Science Foundation of China[62102414] ; National Nature Science Foundation of China[62172415] ; National Nature Science Foundation of China[52175493] ; Open Research Fund Program of State key Laboratory of Hydroscience and Engineering[sklhse-2022-D-04] ; Alibaba Group through Alibaba Innovative Research Program
项目资助者	National Key Research and Development Program of China ; National Nature Science Foundation of China ; Open Research Fund Program of State key Laboratory of Hydroscience and Engineering ; Alibaba Group through Alibaba Innovative Research Program
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS记录号	WOS:001098831500044
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/55166
专题	多模态人工智能系统全国重点实验室
通讯作者	Yuan, Mengke; Wu, Tieru
作者单位	1.Jilin Univ, Sch Math, Changchun 130012, Peoples R China 2.Chinese Acad Sci, Inst Automat, NLPR, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Xu, Jingzhao,Yuan, Mengke,Yan, Dong-Ming,et al. Illumination Guided Attentive Wavelet Network for Low-Light Image Enhancement[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2023,25:6258-6271.
APA	Xu, Jingzhao,Yuan, Mengke,Yan, Dong-Ming,&Wu, Tieru.(2023).Illumination Guided Attentive Wavelet Network for Low-Light Image Enhancement.IEEE TRANSACTIONS ON MULTIMEDIA,25,6258-6271.
MLA	Xu, Jingzhao,et al."Illumination Guided Attentive Wavelet Network for Low-Light Image Enhancement".IEEE TRANSACTIONS ON MULTIMEDIA 25(2023):6258-6271.