Deep unfolding multi-scale regularizer network for image denoising

doi:10.1007/s41095-022-0277-5

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Deep unfolding multi-scale regularizer network for image denoising
	Xu, Jingzhao 3; Yuan, Mengke 1,2; Yan, Dong-Ming 1,2; Wu, Tieru 3
刊名	COMPUTATIONAL VISUAL MEDIA
	2023-06-01
卷号	9 期号:2 页码:335-350
关键词	image denoising deep unfolding network multi-scale regularizer deep learning
ISSN号	2096-0433
DOI	10.1007/s41095-022-0277-5
通讯作者	Wu, Tieru(wutr@jlu.edu.cn)
英文摘要	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.
资助项目	National Key R&D Program of China ; National Nature Science Foundation of China ; [2020YFA0714101] ; [61872162] ; [62102414] ; [62172415] ; [52175493]
WOS关键词	NONLOCAL IMAGE ; SPARSE
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGERNATURE
WOS记录号	WOS:000907570700008
资助机构	National Key R&D Program of China ; National Nature Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/51120]
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.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Jilin Univ, Sch Math, Changchun 130012, 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.