SIA OpenIR  > 机器人学研究室
Deep plug-and-play prior for low-rank tensor completion
Zhao XL(赵熙乐)1; Xu, Wen-Hao1; Jiang TX(蒋太翔)2; Wang Y(王尧)3,4; Ng, Michael K.5
Department机器人学研究室
Source PublicationNeurocomputing
ISSN0925-2312
2020
Volume400Pages:137-149
Indexed BySCI ; EI
EI Accession number20201308337257
WOS IDWOS:000544724700011
Contribution Rank4
Funding OrganizationNational Natural Science Foundation of China ; Fundamental Research Funds for the Central Universities ; HKRGC GRF ; HKU Grant ; China Postdoctoral Science Foundation ; State Key Laboratory of Robotics
KeywordTensor completion Tensor nuclear norm Denoising neural network Alternating direction method of multipliers Plug-and-play framework
Abstract

Multi-dimensional images, such as color images and multi-spectral images (MSIs), are highly correlated and contain abundant spatial and spectral information. However, real-world multi-dimensional images are usually corrupted by missing entries. By integrating deterministic low-rankness prior to the data-driven deep prior, we suggest a novel regularized tensor completion model for multi-dimensional image completion. In the objective function, we adopt the newly emerged tensor nuclear norm (TNN) to characterize the global low-rankness prior of multi-dimensional images. We also formulate an implicit regularizer by plugging a denoising neural network (termed as deep denoiser), which is convinced to express the deep image prior learned from a large number of natural images. The resulting model can be solved by the alternating directional method of multipliers algorithm under the plug-and-play (PnP) framework. Experimental results on color images, videos, and MSIs demonstrate that the proposed method can recover both the global structure and fine details very well and achieve superior performance over competing methods in terms of quality metrics and visual effects.

Language英语
WOS SubjectComputer Science, Artificial Intelligence
WOS KeywordIMAGE-RESTORATION ; MATRIX FACTORIZATION ; NEURAL-NETWORKS ; RECOVERY ; SPARSE
WOS Research AreaComputer Science
Funding ProjectNational Natural Science Foundation of China[61876203] ; National Natural Science Foundation of China[61772003] ; National Natural Science Foundation of China[11971374] ; Fundamental Research Funds for the Central Universities[JBK2001011] ; HKRGC GRF[12306616] ; HKRGC GRF[12200317] ; HKRGC GRF[12300218] ; HKRGC GRF[12300519] ; HKU Grant[104005583] ; China Postdoctoral Science Foundation[2017M610628] ; China Postdoctoral Science Foundation[2018T111031] ; State Key Laboratory of Robotics[2019-O06]
Citation statistics
Cited Times:6[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/26637
Collection机器人学研究室
Corresponding AuthorJiang TX(蒋太翔)
Affiliation1.School of Mathematical Sciences/Research Center for Image and Vision Computing, University of Electronic Science and Technology of China, Chengdu, Sichuan 611731, China
2.FinTech Innovation Center, Financial Intelligence and Financial Engineering Research Key Laboratory of Sichuan Province, School of Economic Information Engineering, Southwestern University of Finance and Economics, Chengdu, Sichuan 611130, China
3.(School of Management, Xi'an Jiaotong University, Xi'an 710049, China
4.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
5.Department of Mathematics, The University of Hong Kong, Pokfulam, Hong Kong
Recommended Citation
GB/T 7714
Zhao XL,Xu, Wen-Hao,Jiang TX,et al. Deep plug-and-play prior for low-rank tensor completion[J]. Neurocomputing,2020,400:137-149.
APA Zhao XL,Xu, Wen-Hao,Jiang TX,Wang Y,&Ng, Michael K..(2020).Deep plug-and-play prior for low-rank tensor completion.Neurocomputing,400,137-149.
MLA Zhao XL,et al."Deep plug-and-play prior for low-rank tensor completion".Neurocomputing 400(2020):137-149.
Files in This Item:
File Name/Size DocType Version Access License
Deep plug-and-play p(6634KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhao XL(赵熙乐)]'s Articles
[Xu, Wen-Hao]'s Articles
[Jiang TX(蒋太翔)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhao XL(赵熙乐)]'s Articles
[Xu, Wen-Hao]'s Articles
[Jiang TX(蒋太翔)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhao XL(赵熙乐)]'s Articles
[Xu, Wen-Hao]'s Articles
[Jiang TX(蒋太翔)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Deep plug-and-play prior for low-rank tensor completion.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.