Reconciliation Of Group Sparsity And Low-Rank Models For Image Restoration

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 t...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (IEEE International Conference on Multimedia and Expo) pp. 1 - 6
Main Authors: Zha, Zhiyuan, Wen, Bihan, Yuan, Xin, Zhou, Jiantao, Zhu, Ce
Format: Conference Proceeding
Language:English
Published: IEEE 01.07.2020
Subjects:
Adaptation models
adaptive parameter adjustment
alternating minimization
Dictionaries
Encoding
Group sparse coding
Image coding
Image denoising
Image restoration
low-rank regularized group sparse coding
Minimization
ISSN:1945-788X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract 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.
AbstractList 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.
Author Yuan, Xin
Zhu, Ce
Zhou, Jiantao
Wen, Bihan
Zha, Zhiyuan
Author_xml – sequence: 1
  givenname: Zhiyuan
  surname: Zha
  fullname: Zha, Zhiyuan
  organization: Nanyang Technological University,School of Electrical & Electronic Engineering,Singapore,639798
– sequence: 2
  givenname: Bihan
  surname: Wen
  fullname: Wen, Bihan
  organization: Nanyang Technological University,School of Electrical & Electronic Engineering,Singapore,639798
– sequence: 3
  givenname: Xin
  surname: Yuan
  fullname: Yuan, Xin
  organization: Nokia Bell Labs, 600 Mountain Avenue,Murray Hill,NJ,USA,07974
– sequence: 4
  givenname: Jiantao
  surname: Zhou
  fullname: Zhou, Jiantao
  organization: University of Macau,Department of Computer and Information Science,Macau,China,999078
– sequence: 5
  givenname: Ce
  surname: Zhu
  fullname: Zhu, Ce
  organization: University of Electronic Science and Technology of China,Chengdu,China,611731
BookMark eNotj11LwzAYRqMouM39AkHyB1rffLRJLkfZZqVjUBW8G2_TVKJdU9qK7N8ruufmXJ0Dz5xcdaFzhNwziBkD85Bnu7VMuZYxBw6xYcCNgAsyZ4prxoRg-pLMmJFJpLR-uyHLcfyA3ykpDYgZeSqdDZ31rcfJh47uG7odwldPn3scRj-d6KqraRG-oxK7T7oLtWtHugkDzY_47mjpxikMf-4tuW6wHd3yzAV53axfsseo2G_zbFVEnoOYosYYsDqtIeUSRWKNgjpp0jpNnEoVQykkV5BUtsKmQVOhlrW1vHLINcdKiQW5--9659yhH_wRh9PhfF38AAIsT8k
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICME46284.2020.9102930
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISBN 1728113318
9781728113319
EISSN 1945-788X
EndPage 6
ExternalDocumentID 9102930
Genre orig-research
GroupedDBID 6IE
6IF
6IK
6IL
6IN
AAJGR
AAWTH
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IPLJI
OCL
RIE
RIL
RNS
ID FETCH-LOGICAL-i203t-f990c86d0624a35c970d5f6d65e7671a4342705bcbaffa9ba84dcc2bea282ab73
IEDL.DBID RIE
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000612843900197&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:33:55 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-f990c86d0624a35c970d5f6d65e7671a4342705bcbaffa9ba84dcc2bea282ab73
PageCount 6
ParticipantIDs ieee_primary_9102930
PublicationCentury 2000
PublicationDate 2020-July
PublicationDateYYYYMMDD 2020-07-01
PublicationDate_xml – month: 07
  year: 2020
  text: 2020-July
PublicationDecade 2020
PublicationTitle Proceedings (IEEE International Conference on Multimedia and Expo)
PublicationTitleAbbrev ICME
PublicationYear 2020
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0000744903
Score 1.7676097
Snippet Image nonlocal self-similanty (NSS) property has been widely exploited via various sparsity models such as joint sparsity (JS) and group sparse coding (GSC)....
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Adaptation models
adaptive parameter adjustment
alternating minimization
Dictionaries
Encoding
Group sparse coding
Image coding
Image denoising
Image restoration
low-rank regularized group sparse coding
Minimization
Title Reconciliation Of Group Sparsity And Low-Rank Models For Image Restoration
URI https://ieeexplore.ieee.org/document/9102930
WOSCitedRecordID wos000612843900197&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JSwMxFA61ePDk0oo7OXh02swkk8wcpbRYqbXUhd7KyzJQrDOli_59k8xYEbx4C4FH4IXky1u-fAhdq1Cn1DAIGCgboHBtAgCl7UMulkkIBJQvF7wOxHCYTCbpqIZutlwYY4xvPjMtN_S1fF2ojUuVtS20WXSyAfqOELzkam3zKRYKWUpoRQIOSdrudx66jnnpMicRaVXGv1RUPIj09v-3_AFq_rDx8GiLM4eoZvIjtP8tx4Cr09lA9y6UzNVsXnobP2bYZ5bw0wJ86wW-zTUeFJ_BGPI37FTQ5ivcK5a4_25vFTz2IjPetoleet3nzl1QSSUEs4jQdZBZUFEJ14RHDGisUkF0nHHNYyO4CIFRFgkSSyUhyyCVkDCtVCQN2JALpKDHqJ4XuTlBmKWaUUkFYTRjobXNlCTcKMo0B2myU9Rwrpkuyt8wppVXzv6ePkd7zvtlg-sFqq-XG3OJdtXHerZaXvkt_AISoJ2j
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwGA1DBX2auol38-Cj3dImTdtHGRubdnPMKXsbucJwtmMX_fsmaZ0IvvgWAh-ELyQn3-XkAHArfJlgRZhHmDABCpXKY0xI85ALeewzxIQrF7ym0WAQTybJsALutlwYpZRrPlMNO3S1fJmLjU2VNQ20GXQyAfpuSEiACrbWNqNiwJAkCJc0YB8lzV6r37bcS5s7CVCjNP-lo-JgpFP93wIOQf2HjweHW6Q5AhWVHYPqtyADLM9nDTzYYDITs3nhb_ikocstwecFc80X8D6TMM0_vRHL3qDVQZuvYCdfwt67uVfgyMnMONs6eOm0x62uV4oleLMA4bWnDayImEpEA8JwKJIIyVBTSUMV0chnBJMgQiEXnGnNEs5iIoUIuGIm6GI8widgJ8szdQogSSTBHEeIYE18Y6sFR1QJTCRlXOkzULOumS6K_zCmpVfO_56-AfvdcT-dpr3B4wU4sDtRtLtegp31cqOuwJ74WM9Wy2u3nV92NaDq
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=Proceedings+%28IEEE+International+Conference+on+Multimedia+and+Expo%29&rft.atitle=Reconciliation+Of+Group+Sparsity+And+Low-Rank+Models+For+Image+Restoration&rft.au=Zha%2C+Zhiyuan&rft.au=Wen%2C+Bihan&rft.au=Yuan%2C+Xin&rft.au=Zhou%2C+Jiantao&rft.date=2020-07-01&rft.pub=IEEE&rft.eissn=1945-788X&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FICME46284.2020.9102930&rft.externalDocID=9102930