Deep unfolding multi-scale regularizer network for image denoising

doi:10.1007/s41095-022-0277-5

	Deep unfolding multi-scale regularizer network for image denoising
	Xu, Jingzhao 1; Yuan, Mengke2,3 ; Yan, Dong-Ming2,3 ; Wu, Tieru 1
发表期刊	COMPUTATIONAL VISUAL MEDIA
ISSN	2096-0433
	2023-06-01
卷号	9 期号:2 页码:335-350
通讯作者	Wu, Tieru(wutr@jlu.edu.cn)
摘要	Existing deep unfolding methods unroll an optimization algorithm with a fixed number of steps, and utilize convolutional neural networks (CNNs) to learn data-driven priors. However, their performance is limited for two main reasons. Firstly, priors learned in deep feature space need to be converted to the image space at each iteration step, which limits the depth of CNNs and prevents CNNs from exploiting contextual information. Secondly, existing methods only learn deep priors at the single full-resolution scale, so ignore the benefits of multi-scale context in dealing with high level noise. To address these issues, we explicitly consider the image denoising process in the deep feature space and propose the deep unfolding multi-scale regularizer network (DUMRN) for image denoising. The core of DUMRN is the feature-based denoising module (FDM) that directly removes noise in the deep feature space. In each FDM, we construct a multi-scale regularizer block to learn deep prior information from multi-resolution features. We build the DUMRN by stacking a sequence of FDMs and train it in an end-to-end manner. Experimental results on synthetic and real-world benchmarks demonstrate that DUMRN performs favorably compared to state-of-the-art methods.
关键词	image denoising deep unfolding network multi-scale regularizer deep learning
DOI	10.1007/s41095-022-0277-5
关键词[WOS]	NONLOCAL IMAGE ; SPARSE
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China ; National Nature Science Foundation of China ; [2020YFA0714101] ; [61872162] ; [62102414] ; [62172415] ; [52175493]
项目资助者	National Key R&D Program of China ; National Nature Science Foundation of China
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:000907570700008
出版者	SPRINGERNATURE
引用统计	被引频次：5[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/173211/51121
专题	多模态人工智能系统全国重点实验室
通讯作者	Wu, Tieru
作者单位	1.Jilin Univ, Sch Math, Changchun 130012, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Xu, Jingzhao,Yuan, Mengke,Yan, Dong-Ming,et al. Deep unfolding multi-scale regularizer network for image denoising[J]. COMPUTATIONAL VISUAL MEDIA,2023,9(2):335-350.
APA	Xu, Jingzhao,Yuan, Mengke,Yan, Dong-Ming,&Wu, Tieru.(2023).Deep unfolding multi-scale regularizer network for image denoising.COMPUTATIONAL VISUAL MEDIA,9(2),335-350.
MLA	Xu, Jingzhao,et al."Deep unfolding multi-scale regularizer network for image denoising".COMPUTATIONAL VISUAL MEDIA 9.2(2023):335-350.