No Cover Image

Journal article 980 views 432 downloads

Image restoration with group sparse representation and low‐rank group residual learning

Zhaoyuan Cai, Xianghua Xie Orcid Logo, Jingjing Deng, Zengfa Dou Orcid Logo, Bo Tong, Xiaoke Ma Orcid Logo

IET Image Processing, Volume: 18, Issue: 3, Pages: 741 - 760

Swansea University Author: Xianghua Xie Orcid Logo

  • 64966.pdf

    PDF | Version of Record

    © 2023 The Authors. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.

    Download (10.48MB)

Check full text

DOI (Published version): 10.1049/ipr2.12982

Abstract

Image restoration, as a fundamental research topic of image processing, is to reconstruct the original image from degraded signal using the prior knowledge of image. Group sparse representation (GSR) is powerful for image restoration; it however often leads to undesirable sparse solutions in practic...

Full description

Published in: IET Image Processing
ISSN: 1751-9659 1751-9667
Published: Wiley 2024
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa64966
first_indexed 2023-11-12T21:48:44Z
last_indexed 2025-06-18T04:39:41Z
id cronfa64966
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-06-17T16:46:52.1434710</datestamp><bib-version>v2</bib-version><id>64966</id><entry>2023-11-12</entry><title>Image restoration with group sparse representation and low&#x2010;rank group residual learning</title><swanseaauthors><author><sid>b334d40963c7a2f435f06d2c26c74e11</sid><ORCID>0000-0002-2701-8660</ORCID><firstname>Xianghua</firstname><surname>Xie</surname><name>Xianghua Xie</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-11-12</date><deptcode>MACS</deptcode><abstract>Image restoration, as a fundamental research topic of image processing, is to reconstruct the original image from degraded signal using the prior knowledge of image. Group sparse representation (GSR) is powerful for image restoration; it however often leads to undesirable sparse solutions in practice. In order to improve the quality of image restoration based on GSR, the sparsity residual model expects the representation learned from degraded images to be as close as possible to the true representation. In this article, a group residual learning based on low-rank self-representation is proposed to automatically estimate the true group sparse representation. It makes full use of the relation among patches and explores the subgroup structures within the same group, which makes the sparse residual model have better interpretation furthermore, results in high-quality restored images. Extensive experimental results on two typical image restoration tasks (image denoising and deblocking) demonstrate that the proposed algorithm outperforms many other popular or state-of-the-art image restoration methods.</abstract><type>Journal Article</type><journal>IET Image Processing</journal><volume>18</volume><journalNumber>3</journalNumber><paginationStart>741</paginationStart><paginationEnd>760</paginationEnd><publisher>Wiley</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1751-9659</issnPrint><issnElectronic>1751-9667</issnElectronic><keywords>group residual learning, group sparse representation, image restoration, low-rank self-representation</keywords><publishedDay>28</publishedDay><publishedMonth>2</publishedMonth><publishedYear>2024</publishedYear><publishedDate>2024-02-28</publishedDate><doi>10.1049/ipr2.12982</doi><url/><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm>Other</apcterm><funders>This work was supported by the Shaanxi Key Research and Development Program (Program No. 2021ZDLGY02-02).</funders><projectreference/><lastEdited>2025-06-17T16:46:52.1434710</lastEdited><Created>2023-11-12T21:42:50.3256973</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Zhaoyuan</firstname><surname>Cai</surname><order>1</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><orcid>0000-0002-2701-8660</orcid><order>2</order></author><author><firstname>Jingjing</firstname><surname>Deng</surname><order>3</order></author><author><firstname>Zengfa</firstname><surname>Dou</surname><orcid>0000-0002-5162-6244</orcid><order>4</order></author><author><firstname>Bo</firstname><surname>Tong</surname><order>5</order></author><author><firstname>Xiaoke</firstname><surname>Ma</surname><orcid>0000-0002-5604-7137</orcid><order>6</order></author></authors><documents><document><filename>64966__29068__a0508ceeda294222a8e379b96f6b2743.pdf</filename><originalFilename>64966.pdf</originalFilename><uploaded>2023-11-21T10:53:33.7028194</uploaded><type>Output</type><contentLength>10984068</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2023 The Authors. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2025-06-17T16:46:52.1434710 v2 64966 2023-11-12 Image restoration with group sparse representation and low‐rank group residual learning b334d40963c7a2f435f06d2c26c74e11 0000-0002-2701-8660 Xianghua Xie Xianghua Xie true false 2023-11-12 MACS Image restoration, as a fundamental research topic of image processing, is to reconstruct the original image from degraded signal using the prior knowledge of image. Group sparse representation (GSR) is powerful for image restoration; it however often leads to undesirable sparse solutions in practice. In order to improve the quality of image restoration based on GSR, the sparsity residual model expects the representation learned from degraded images to be as close as possible to the true representation. In this article, a group residual learning based on low-rank self-representation is proposed to automatically estimate the true group sparse representation. It makes full use of the relation among patches and explores the subgroup structures within the same group, which makes the sparse residual model have better interpretation furthermore, results in high-quality restored images. Extensive experimental results on two typical image restoration tasks (image denoising and deblocking) demonstrate that the proposed algorithm outperforms many other popular or state-of-the-art image restoration methods. Journal Article IET Image Processing 18 3 741 760 Wiley 1751-9659 1751-9667 group residual learning, group sparse representation, image restoration, low-rank self-representation 28 2 2024 2024-02-28 10.1049/ipr2.12982 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University Other This work was supported by the Shaanxi Key Research and Development Program (Program No. 2021ZDLGY02-02). 2025-06-17T16:46:52.1434710 2023-11-12T21:42:50.3256973 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Zhaoyuan Cai 1 Xianghua Xie 0000-0002-2701-8660 2 Jingjing Deng 3 Zengfa Dou 0000-0002-5162-6244 4 Bo Tong 5 Xiaoke Ma 0000-0002-5604-7137 6 64966__29068__a0508ceeda294222a8e379b96f6b2743.pdf 64966.pdf 2023-11-21T10:53:33.7028194 Output 10984068 application/pdf Version of Record true © 2023 The Authors. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made. true eng http://creativecommons.org/licenses/by/4.0/
title Image restoration with group sparse representation and low‐rank group residual learning
spellingShingle Image restoration with group sparse representation and low‐rank group residual learning
Xianghua Xie
title_short Image restoration with group sparse representation and low‐rank group residual learning
title_full Image restoration with group sparse representation and low‐rank group residual learning
title_fullStr Image restoration with group sparse representation and low‐rank group residual learning
title_full_unstemmed Image restoration with group sparse representation and low‐rank group residual learning
title_sort Image restoration with group sparse representation and low‐rank group residual learning
author_id_str_mv b334d40963c7a2f435f06d2c26c74e11
author_id_fullname_str_mv b334d40963c7a2f435f06d2c26c74e11_***_Xianghua Xie
author Xianghua Xie
author2 Zhaoyuan Cai
Xianghua Xie
Jingjing Deng
Zengfa Dou
Bo Tong
Xiaoke Ma
format Journal article
container_title IET Image Processing
container_volume 18
container_issue 3
container_start_page 741
publishDate 2024
institution Swansea University
issn 1751-9659
1751-9667
doi_str_mv 10.1049/ipr2.12982
publisher Wiley
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 1
active_str 0
description Image restoration, as a fundamental research topic of image processing, is to reconstruct the original image from degraded signal using the prior knowledge of image. Group sparse representation (GSR) is powerful for image restoration; it however often leads to undesirable sparse solutions in practice. In order to improve the quality of image restoration based on GSR, the sparsity residual model expects the representation learned from degraded images to be as close as possible to the true representation. In this article, a group residual learning based on low-rank self-representation is proposed to automatically estimate the true group sparse representation. It makes full use of the relation among patches and explores the subgroup structures within the same group, which makes the sparse residual model have better interpretation furthermore, results in high-quality restored images. Extensive experimental results on two typical image restoration tasks (image denoising and deblocking) demonstrate that the proposed algorithm outperforms many other popular or state-of-the-art image restoration methods.
published_date 2024-02-28T06:35:32Z
_version_ 1851283296414072832
score 11.090362

Similar Items