SIA OpenIR  > 机器人学研究室
Low-rank decomposition on transformed feature maps domain for image denoising
Luo Q(罗琼)1,2,3; Liu BC(刘柏辰)1,2,3; Zhang Y(张杨)4; Han Z(韩志)1,2; Tang YD(唐延东)1,2
Department机器人学研究室
Source PublicationVisual Computer
ISSN0178-2789
2020
Pages1-17
Indexed BySCI ; EI
EI Accession number20203209020459
WOS IDWOS:000556153200001
Contribution Rank1
Funding OrganizationNational Natural Science Foundation of China under Grant 61773367, Grant 61303168, and Grant 61821005 ; Youth Innovation Promotion Association of the Chinese Academy of ences under Grant 2016183
KeywordLow-rank Domain transformation Autoencoder Denoising
Abstract

Low-rank based models are proved outstanding for denoising on the data with strong repetitive or redundant property. However, for natural images with complex structures or rich details, the performance drops down because of the weak low-rankness of the data. A feasible solution is to transform the data into a suitable domain to further explore the underlying low-rank information. In this paper, we present a novel approach to create such a domain via a fully replicated linear autoencoder network. By applying various low-rank models to the feature maps generated by the encoder rather than the original data, and then performing inverse transformation by the decoder, their denoising performances all get enhanced. In addition, feature maps also show good sparsity, hence we introduce a new measure combining sparse and low-rank regularity, and further propose corresponding single image denoising model. Extensive experiments show the superiority of our work.

Language英语
WOS SubjectComputer Science, Software Engineering
WOS KeywordRECOVERY ; SPARSE
WOS Research AreaComputer Science
Funding ProjectNational Natural Science Foundation of China[61773367] ; National Natural Science Foundation of China[61303168] ; National Natural Science Foundation of China[61821005] ; Youth Innovation Promotion Association of the Chinese Academy of Sciences[2016183]
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/27480
Collection机器人学研究室
Corresponding AuthorHan Z(韩志)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China
3.University of Chinese Academy of Sciences, Beijing, China
4.Department of Computer Science, City University of Hong Kong, Kowloon Tong
5.Hongkong, China
Recommended Citation
GB/T 7714
Luo Q,Liu BC,Zhang Y,et al. Low-rank decomposition on transformed feature maps domain for image denoising[J]. Visual Computer,2020:1-17.
APA Luo Q,Liu BC,Zhang Y,Han Z,&Tang YD.(2020).Low-rank decomposition on transformed feature maps domain for image denoising.Visual Computer,1-17.
MLA Luo Q,et al."Low-rank decomposition on transformed feature maps domain for image denoising".Visual Computer (2020):1-17.
Files in This Item:
File Name/Size DocType Version Access License
Low-rank decompositi(4892KB)期刊论文出版稿开放获取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
[Luo Q(罗琼)]'s Articles
[Liu BC(刘柏辰)]'s Articles
[Zhang Y(张杨)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Luo Q(罗琼)]'s Articles
[Liu BC(刘柏辰)]'s Articles
[Zhang Y(张杨)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Luo Q(罗琼)]'s Articles
[Liu BC(刘柏辰)]'s Articles
[Zhang Y(张杨)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Low-rank decomposition on transformed feature maps domain for image denoising.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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