UM  > Faculty of Science and Technology
Residential Collegefalse
Reconciliation of group sparsity and low-rank models for image restoration
Zhiyuan Zha1; Bihan Wen1; Xin Yuan2; Jiantao Zhou3; Ce Zhu4
Conference NameIEEE International Conference on Multimedia and Expo (ICME)
Source PublicationProceedings - IEEE International Conference on Multimedia and Expo
Conference Date6-10 July 2020
Conference PlaceLondon, UK

Image nonlocal self-similanty (NSS) property has been widely exploited via various sparsity models such as joint sparsity (JS) and group sparse coding (GSC). However, the existing NSS-based sparsity models are either too restrictive, i.e., JS enforces the sparse codes to share the same support, or too general, i.e., GSC imposes only plain sparsity on the group coefficients, which limit their effectiveness for modeling real images. In this paper, we propose a novel NSS-based sparsity model, namely low-rank regularized group sparse coding (LR-GSC), to bridge the gap between the popular GSC and JS. The proposed LR-GSC model simultaneously exploits the sparsity and low-rankness of the dictionary-domain coefficients for each group of similar patches. To make the proposed scheme tractable and robust, an alternating minimization with an adaptive adjusted parameter strategy is develope- d to solve the proposed optimization problem. Experimental results on both image deblocking and denoising demonstrate that the proposed LR-GSC image restoration algorithms outperform many popular or state-of-the-art methods, in terms of both the objective and perceptual quality.

KeywordAdaptive Parameter Adjustment Alternating Minimization Group Sparse Coding Image Restoration Low-rank Regularized Group Sparse Coding
URLView the original
Indexed ByCPCI-S
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000612843900197
Scopus ID2-s2.0-85090393774
Fulltext Access
Citation statistics
Cited Times [WOS]:10   [WOS Record]     [Related Records in WOS]
Document TypeConference paper
CollectionFaculty of Science and Technology
Affiliation1.School of Electrical & Electronic Engineering, Nanyang Technological University, Singapore 639798
2.Nokia Bell Labs, 600 Mountain Avenue, Murray Hill, NJ, 07974, USA.
3.epartment of Computer and Information Science, University of Macau, Macau 999078, China
4.School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China.
Recommended Citation
GB/T 7714
Zhiyuan Zha,Bihan Wen,Xin Yuan,et al. Reconciliation of group sparsity and low-rank models for image restoration[C],2020.
APA Zhiyuan Zha,Bihan Wen,Xin Yuan,Jiantao Zhou,&Ce Zhu.(2020).Reconciliation of group sparsity and low-rank models for image restoration.Proceedings - IEEE International Conference on Multimedia and Expo,2020-July.
Files in This Item: Download All
File Name/Size Publications Version Access License
Reconciliation_Of_Gr(1608KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhiyuan Zha]'s Articles
[Bihan Wen]'s Articles
[Xin Yuan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhiyuan Zha]'s Articles
[Bihan Wen]'s Articles
[Xin Yuan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhiyuan Zha]'s Articles
[Bihan Wen]'s Articles
[Xin Yuan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Reconciliation_Of_Group_Sparsity_And_Low-Rank_Models_For_Image_Restoration.pdf
Format: Adobe PDF
All comments (0)
No comment.

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