Image Restoration via Reconciliation of Group Sparsity and Low-Rank Models
Image nonlocal self-similarity (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, e.g. , JS enforces the sparse codes to share the same support, or...
Saved in:
| Published in: | IEEE transactions on image processing Vol. 30; pp. 5223 - 5238 |
|---|---|
| Main Authors: | , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
United States
IEEE
01.01.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects: | |
| ISSN: | 1057-7149, 1941-0042, 1941-0042 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Image nonlocal self-similarity (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, e.g. , JS enforces the sparse codes to share the same support, or too general, e.g. , 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. An alternating minimization with an adaptive adjusted parameter strategy is developed to solve the proposed optimization problem for different image restoration tasks, including image denoising, image deblocking, image inpainting, and image compressive sensing. Extensive experimental results demonstrate that the proposed LR-GSC algorithm outperforms many popular or state-of-the-art methods in terms of objective and perceptual metrics. |
|---|---|
| AbstractList | Image nonlocal self-similarity (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, e.g. , JS enforces the sparse codes to share the same support, or too general, e.g. , 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. An alternating minimization with an adaptive adjusted parameter strategy is developed to solve the proposed optimization problem for different image restoration tasks, including image denoising, image deblocking, image inpainting, and image compressive sensing. Extensive experimental results demonstrate that the proposed LR-GSC algorithm outperforms many popular or state-of-the-art methods in terms of objective and perceptual metrics. Image nonlocal self-similarity (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, e.g., JS enforces the sparse codes to share the same support, or too general, e.g., 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. An alternating minimization with an adaptive adjusted parameter strategy is developed to solve the proposed optimization problem for different image restoration tasks, including image denoising, image deblocking, image inpainting, and image compressive sensing. Extensive experimental results demonstrate that the proposed LR-GSC algorithm outperforms many popular or state-of-the-art methods in terms of objective and perceptual metrics.Image nonlocal self-similarity (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, e.g., JS enforces the sparse codes to share the same support, or too general, e.g., 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. An alternating minimization with an adaptive adjusted parameter strategy is developed to solve the proposed optimization problem for different image restoration tasks, including image denoising, image deblocking, image inpainting, and image compressive sensing. Extensive experimental results demonstrate that the proposed LR-GSC algorithm outperforms many popular or state-of-the-art methods in terms of objective and perceptual metrics. |
| Author | Yuan, Xin Zhu, Ce Zhou, Jiantao Wen, Bihan Zha, Zhiyuan |
| Author_xml | – sequence: 1 givenname: Zhiyuan orcidid: 0000-0002-5515-5339 surname: Zha fullname: Zha, Zhiyuan email: zhiyuan.zha@ntu.edu.sg organization: School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore – sequence: 2 givenname: Bihan orcidid: 0000-0002-6874-6453 surname: Wen fullname: Wen, Bihan email: bihan.wen@ntu.edu.sg organization: School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore – sequence: 3 givenname: Xin orcidid: 0000-0002-8311-7524 surname: Yuan fullname: Yuan, Xin email: xyuan@bell-labs.com organization: Nokia Bell Labs, Murray Hill, NJ, USA – sequence: 4 givenname: Jiantao orcidid: 0000-0002-6015-2618 surname: Zhou fullname: Zhou, Jiantao email: jtzhou@umac.mo organization: Department of Computer and Information Science, State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China – sequence: 5 givenname: Ce orcidid: 0000-0001-7607-707X surname: Zhu fullname: Zhu, Ce email: eczhu@uestc.edu.cn organization: School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/34010133$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kctLwzAcx4Mo7qF3QZCCFy-dvzz6yFGGzslEmbuXNE0ls2tm0ir7783s3GEHD3ny-SZfvt8BOq5NrRC6wDDCGPjtYvo6IkDwiEKSUsKPUB9zhkMARo79HqIkTDDjPTRwbgmAWYTjU9SjDDBgSvvoaboS7yqYK9cYKxpt6uBLC3-Wppa60t2VKYOJNe06eFsL63SzCURdBDPzHc5F_RE8m0JV7gydlKJy6ny3DtHi4X4xfgxnL5Pp-G4WSsqSxs-x9J455WlM0qRgPM85KzjjkNJECJIWkspSxILwMldEUZACUsC5HyqmQ3TTPbu25rP1vrOVdlJVlaiVaV1GIsI5SdKIefT6AF2a1tbenKcooT6CCHvqake1-UoV2drqlbCb7C8kD0AHSGucs6rcIxiybQ-Z7yHb9pDtevCS-EAidfObZWOFrv4TXnZCrZTa_8MZjXgc0R-DApH_ |
| CODEN | IIPRE4 |
| CitedBy_id | crossref_primary_10_3390_math10203810 crossref_primary_10_1109_TIP_2021_3086049 crossref_primary_10_1016_j_dsp_2021_103270 crossref_primary_10_1109_TNNLS_2022_3144630 crossref_primary_10_1109_TCI_2023_3244396 crossref_primary_10_1109_TMM_2024_3521833 crossref_primary_10_1016_j_sigpro_2024_109513 crossref_primary_10_1109_JSTARS_2025_3568783 crossref_primary_10_1016_j_asoc_2024_111322 crossref_primary_10_1109_TCI_2022_3224281 crossref_primary_10_1088_1361_6560_ad8c98 crossref_primary_10_1016_j_ijleo_2023_171013 crossref_primary_10_1016_j_optlastec_2023_110061 crossref_primary_10_1016_j_sigpro_2023_109191 crossref_primary_10_1016_j_phycom_2023_102231 crossref_primary_10_1049_ipr2_12982 crossref_primary_10_1016_j_patcog_2025_111697 crossref_primary_10_1049_ipr2_12583 crossref_primary_10_1186_s13634_021_00798_4 crossref_primary_10_3390_s23062888 crossref_primary_10_1016_j_sigpro_2022_108896 crossref_primary_10_1109_JSTARS_2023_3244069 crossref_primary_10_3390_rs14194797 crossref_primary_10_1016_j_sigpro_2023_109284 crossref_primary_10_1016_j_jvcir_2022_103723 crossref_primary_10_1016_j_sigpro_2022_108690 crossref_primary_10_1109_JSTARS_2023_3301149 crossref_primary_10_1007_s10489_022_03259_z crossref_primary_10_1016_j_sigpro_2025_110220 crossref_primary_10_1117_1_JEI_31_4_043012 crossref_primary_10_1016_j_ins_2023_04_010 crossref_primary_10_1016_j_sigpro_2022_108650 crossref_primary_10_1109_TIP_2022_3176220 crossref_primary_10_1007_s11045_023_00867_x crossref_primary_10_3390_s22051893 crossref_primary_10_1016_j_dsp_2022_103694 crossref_primary_10_1016_j_patcog_2022_109040 crossref_primary_10_1016_j_sigpro_2022_108926 crossref_primary_10_1109_TAI_2023_3323628 crossref_primary_10_1109_TSIPN_2022_3169633 crossref_primary_10_1007_s00371_023_02786_1 crossref_primary_10_1109_LSP_2023_3241847 crossref_primary_10_1109_TCYB_2023_3251730 crossref_primary_10_1016_j_dsp_2023_104029 crossref_primary_10_1109_TCI_2024_3384812 crossref_primary_10_1109_TIP_2023_3242589 crossref_primary_10_1109_TMM_2023_3324490 crossref_primary_10_1016_j_sigpro_2024_109536 crossref_primary_10_1109_TIFS_2023_3337717 crossref_primary_10_1016_j_knosys_2022_108590 crossref_primary_10_1007_s11465_023_0762_2 crossref_primary_10_1109_JSEN_2023_3306769 crossref_primary_10_3390_math12091412 crossref_primary_10_1016_j_optlaseng_2022_107413 crossref_primary_10_1109_TCSVT_2023_3306811 crossref_primary_10_1016_j_imavis_2024_105210 crossref_primary_10_1109_TCYB_2021_3084931 crossref_primary_10_1016_j_inffus_2025_103013 crossref_primary_10_1016_j_cviu_2024_104216 crossref_primary_10_1007_s41965_024_00173_w crossref_primary_10_1109_TCSVT_2022_3165587 crossref_primary_10_1016_j_cam_2025_116695 crossref_primary_10_1016_j_dsp_2025_105169 crossref_primary_10_1109_ACCESS_2024_3442373 crossref_primary_10_1109_TCSVT_2022_3233589 crossref_primary_10_1007_s11042_023_16636_8 crossref_primary_10_1016_j_asoc_2023_110861 crossref_primary_10_3390_electronics14020353 crossref_primary_10_1088_1361_6420_ad0c42 |
| Cites_doi | 10.1007/s101070100280 10.1109/CVPR.2016.55 10.1007/978-3-030-01261-8_27 10.1109/TVCG.2017.2702738 10.1109/TPAMI.2010.161 10.1109/CVPR.2005.38 10.1109/JETCAS.2012.2220391 10.1109/TIP.2018.2875569 10.1109/TIP.2013.2274386 10.1109/TIP.2020.3005515 10.1109/TIP.2017.2651400 10.1109/TIP.2012.2221729 10.1109/ALLERTON.2015.7447163 10.1109/TIP.2016.2627807 10.1109/TIP.2011.2160072 10.1109/TIP.2016.2515985 10.1109/TIP.2014.2323127 10.1007/s11263-014-0761-1 10.1109/ICCV.2015.36 10.1109/TPAMI.2016.2596743 10.1109/ICME.2017.8019334 10.1109/TIP.2020.3015545 10.1137/100817206 10.1007/s00371-016-1318-9 10.1109/TCSVT.2014.2302380 10.1109/TIP.2003.819861 10.1109/TSP.2012.2226445 10.1137/040605412 10.1109/TIP.2016.2562563 10.1109/TIP.2013.2257813 10.1109/TMM.2016.2614427 10.1109/TIP.2007.901238 10.1109/TIP.2017.2662206 10.1109/CVPR.2017.411 10.1109/TNNLS.2021.3057439 10.1109/ICIP40778.2020.9190707 10.1109/LSP.2017.2731791 10.1109/CVPR42600.2020.00196 10.1109/TIP.2010.2076294 10.1109/TIP.2018.2862357 10.1109/18.382009 10.1109/ICCV.2019.00259 10.1109/CVPR.2018.00984 10.1007/978-3-030-58542-6_15 10.1109/ICCV.2009.5459452 10.1109/TIP.2018.2839891 10.1007/s11263-016-0930-5 10.1109/TIP.2015.2446943 10.1109/TIP.2018.2867943 10.1109/83.862633 10.1007/s11263-015-0808-y 10.1016/0167-2789(92)90242-F 10.1109/TCSVT.2016.2556498 10.1109/CVPR.2017.300 10.1109/TCSVT.2016.2580399 10.1109/CVPR.2014.366 10.1109/TIP.2020.3021291 10.1109/TIP.2012.2235847 10.1109/TIP.2020.2972109 10.1109/ICCV.2011.6126278 10.1109/CVPR.2018.00196 10.1109/ICCV.2015.73 10.1109/ICME46284.2020.9102930 10.1109/MSP.2020.3023869 10.1109/TIP.2016.2590318 10.1137/080738970 10.1109/TIP.2019.2928136 10.1109/TBME.2012.2217493 10.1109/TIP.2019.2958309 10.1109/TIP.2006.881969 10.1109/TIP.2007.891788 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| DOI | 10.1109/TIP.2021.3078329 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore Digital Library CrossRef PubMed Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional MEDLINE - Academic |
| DatabaseTitleList | Technology Research Database PubMed MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE/IET Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Engineering |
| EISSN | 1941-0042 |
| EndPage | 5238 |
| ExternalDocumentID | 34010133 10_1109_TIP_2021_3078329 9435965 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: Ministry of Education, Republic of Singapore, under its Academic Research Fund Tier 1 Project RG137/20 and the Start-Up Grant – fundername: Rapid-Rich Object Search (ROSE) Laboratory, Nanyang Technological University, Singapore funderid: 10.13039/501100001475 – fundername: Macau Science and Technology Development Fund, Macau SAR grantid: 077/2018/A2; 0060/2019/A1 – fundername: National Natural Science Foundation of China grantid: 62020106011; U19A2052; 61971476 funderid: 10.13039/501100001809 |
| GroupedDBID | --- -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS TAE TN5 VH1 AAYXX CITATION NPM Z5M 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| ID | FETCH-LOGICAL-c347t-c36c20293986287d49bb94d9490837aa28dc3cfa6a29fbe2e30ca0801b801e63 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 76 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000655246800008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1057-7149 1941-0042 |
| IngestDate | Sat Sep 27 18:19:08 EDT 2025 Mon Jun 30 10:19:57 EDT 2025 Wed Feb 19 02:28:22 EST 2025 Sat Nov 29 03:21:14 EST 2025 Tue Nov 18 22:41:40 EST 2025 Wed Aug 27 02:51:10 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c347t-c36c20293986287d49bb94d9490837aa28dc3cfa6a29fbe2e30ca0801b801e63 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-6015-2618 0000-0002-6874-6453 0000-0002-5515-5339 0000-0002-8311-7524 0000-0001-7607-707X |
| PMID | 34010133 |
| PQID | 2532301351 |
| PQPubID | 85429 |
| PageCount | 16 |
| ParticipantIDs | pubmed_primary_34010133 proquest_journals_2532301351 crossref_primary_10_1109_TIP_2021_3078329 ieee_primary_9435965 proquest_miscellaneous_2529927854 crossref_citationtrail_10_1109_TIP_2021_3078329 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-01-01 |
| PublicationDateYYYYMMDD | 2021-01-01 |
| PublicationDate_xml | – month: 01 year: 2021 text: 2021-01-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: New York |
| PublicationTitle | IEEE transactions on image processing |
| PublicationTitleAbbrev | TIP |
| PublicationTitleAlternate | IEEE Trans Image Process |
| PublicationYear | 2021 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref13 zeyde (ref80) 2010 ref56 ref12 ref59 ref15 zhang (ref72) 2013 ref58 ref14 ref53 ref52 ref55 ref54 ref10 ref17 ref16 ref19 ref18 shi (ref77) 2020; 29 liu (ref8) 2018 ren (ref57) 2013 ref51 ref50 ref46 ref48 ref47 ref42 ref41 ref44 wang (ref24) 2012 ref49 mastan (ref9) 2021 ref7 ref4 ref3 ref6 ref5 ref81 ref40 wen (ref31) 2020 ref79 ref35 ref78 ref34 ref37 ref36 ref75 ref74 ref30 ref33 ref76 ref32 ref2 ref1 ref39 ref38 ref71 ref70 ref73 ref68 ref67 ref23 ref26 ref69 ref25 ref64 ref20 ref63 boyd (ref43) 2011 ref66 ref22 ref65 ref21 avriel (ref45) 2003 ref28 ref27 ref29 ref60 mataev (ref11) 2019 ref62 ref61 |
| References_xml | – ident: ref44 doi: 10.1007/s101070100280 – ident: ref38 doi: 10.1109/CVPR.2016.55 – start-page: 2836 year: 2013 ident: ref72 article-title: Improved total variation based image compressive sensing recovery by nonlocal regularization publication-title: Proc IEEE Int Symp Circuits Syst (ISCAS) – ident: ref63 doi: 10.1007/978-3-030-01261-8_27 – ident: ref69 doi: 10.1109/TVCG.2017.2702738 – ident: ref51 doi: 10.1109/TPAMI.2010.161 – ident: ref15 doi: 10.1109/CVPR.2005.38 – ident: ref73 doi: 10.1109/JETCAS.2012.2220391 – ident: ref71 doi: 10.1109/TIP.2018.2875569 – ident: ref56 doi: 10.1109/TIP.2013.2274386 – ident: ref35 doi: 10.1109/TIP.2020.3005515 – ident: ref48 doi: 10.1109/TIP.2017.2651400 – ident: ref6 doi: 10.1109/TIP.2012.2221729 – start-page: 2897 year: 2021 ident: ref9 article-title: DeepCFL: Deep contextual features learning from a single image publication-title: Proc IEEE/CVF Winter Conf Appl Comput Vis – year: 2003 ident: ref45 publication-title: Nonlinear Programming Analysis and Methods – ident: ref75 doi: 10.1109/ALLERTON.2015.7447163 – start-page: 711 year: 2010 ident: ref80 article-title: On single image scale-up using sparse-representations publication-title: Proc Int Conf Curves Surf – ident: ref79 doi: 10.1109/TIP.2016.2627807 – ident: ref37 doi: 10.1109/TIP.2011.2160072 – ident: ref30 doi: 10.1109/TIP.2016.2515985 – ident: ref12 doi: 10.1109/TIP.2014.2323127 – ident: ref4 doi: 10.1007/s11263-014-0761-1 – ident: ref21 doi: 10.1109/ICCV.2015.36 – ident: ref54 doi: 10.1109/TPAMI.2016.2596743 – ident: ref33 doi: 10.1109/ICME.2017.8019334 – ident: ref17 doi: 10.1109/TIP.2020.3015545 – ident: ref5 doi: 10.1137/100817206 – ident: ref39 doi: 10.1007/s00371-016-1318-9 – year: 2020 ident: ref31 article-title: A set-theoretic study of the relationships of image models and priors for restoration problems publication-title: arXiv 2003 12985 – ident: ref66 doi: 10.1109/TCSVT.2014.2302380 – ident: ref53 doi: 10.1109/TIP.2003.819861 – ident: ref14 doi: 10.1109/TSP.2012.2226445 – ident: ref2 doi: 10.1137/040605412 – ident: ref74 doi: 10.1109/TIP.2016.2562563 – start-page: 1 year: 2019 ident: ref11 article-title: DeepRED: Deep image prior powered by red publication-title: Proc IEEE/CVF Int Conf Comput Vis Workshops – ident: ref81 doi: 10.1109/TIP.2013.2257813 – ident: ref20 doi: 10.1109/TMM.2016.2614427 – ident: ref19 doi: 10.1109/TIP.2007.901238 – ident: ref78 doi: 10.1109/TIP.2017.2662206 – ident: ref29 doi: 10.1109/CVPR.2017.411 – ident: ref23 doi: 10.1109/TNNLS.2021.3057439 – ident: ref10 doi: 10.1109/ICIP40778.2020.9190707 – ident: ref18 doi: 10.1109/LSP.2017.2731791 – ident: ref55 doi: 10.1109/CVPR42600.2020.00196 – ident: ref65 doi: 10.1109/TIP.2010.2076294 – ident: ref49 doi: 10.1109/TIP.2018.2862357 – ident: ref42 doi: 10.1109/18.382009 – ident: ref64 doi: 10.1109/ICCV.2019.00259 – ident: ref70 doi: 10.1109/CVPR.2018.00984 – ident: ref28 doi: 10.1007/978-3-030-58542-6_15 – ident: ref16 doi: 10.1109/ICCV.2009.5459452 – ident: ref62 doi: 10.1109/TIP.2018.2839891 – start-page: 516 year: 2013 ident: ref57 article-title: Image blocking artifacts reduction via patch clustering and low-rank minimization publication-title: Proc Data Compress Conf – ident: ref25 doi: 10.1007/s11263-016-0930-5 – ident: ref67 doi: 10.1109/TIP.2015.2446943 – ident: ref59 doi: 10.1109/TIP.2018.2867943 – ident: ref52 doi: 10.1109/83.862633 – ident: ref22 doi: 10.1007/s11263-015-0808-y – start-page: 1673 year: 2018 ident: ref8 article-title: Non-local recurrent network for image restoration publication-title: Proc Adv Neural Inf Process Syst – ident: ref1 doi: 10.1016/0167-2789(92)90242-F – start-page: 231 year: 2012 ident: ref24 article-title: Nonlocal spectral prior model for low-level vision publication-title: Proc Asian Conf Comput Vis – ident: ref68 doi: 10.1109/TCSVT.2016.2556498 – ident: ref61 doi: 10.1109/CVPR.2017.300 – ident: ref58 doi: 10.1109/TCSVT.2016.2580399 – ident: ref7 doi: 10.1109/CVPR.2014.366 – year: 2011 ident: ref43 publication-title: Distributed optimization and statistical learning via the alternating direction method of multipliers – ident: ref50 doi: 10.1109/TIP.2020.3021291 – ident: ref36 doi: 10.1109/TIP.2012.2235847 – ident: ref13 doi: 10.1109/TIP.2020.2972109 – ident: ref46 doi: 10.1109/ICCV.2011.6126278 – ident: ref76 doi: 10.1109/CVPR.2018.00196 – ident: ref60 doi: 10.1109/ICCV.2015.73 – ident: ref32 doi: 10.1109/ICME46284.2020.9102930 – ident: ref40 doi: 10.1109/MSP.2020.3023869 – ident: ref47 doi: 10.1109/TIP.2016.2590318 – ident: ref34 doi: 10.1137/080738970 – volume: 29 start-page: 375 year: 2020 ident: ref77 article-title: Image compressed sensing using convolutional neural network publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2019.2928136 – ident: ref27 doi: 10.1109/TBME.2012.2217493 – ident: ref26 doi: 10.1109/TIP.2019.2958309 – ident: ref3 doi: 10.1109/TIP.2006.881969 – ident: ref41 doi: 10.1109/TIP.2007.891788 |
| SSID | ssj0014516 |
| Score | 2.5841334 |
| Snippet | Image nonlocal self-similarity (NSS) property has been widely exploited via various sparsity models such as joint sparsity (JS) and group sparse coding (GSC).... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 5223 |
| SubjectTerms | Adaptation models adaptive parameter adjustment Algorithms alternating minimization Coding Dictionaries Group sparse coding Image coding Image denoising Image restoration low-rank regularized group sparse coding Mathematical models Minimization Noise reduction Optimization Self-similarity Sparse matrices Sparsity |
| Title | Image Restoration via Reconciliation of Group Sparsity and Low-Rank Models |
| URI | https://ieeexplore.ieee.org/document/9435965 https://www.ncbi.nlm.nih.gov/pubmed/34010133 https://www.proquest.com/docview/2532301351 https://www.proquest.com/docview/2529927854 |
| Volume | 30 |
| WOSCitedRecordID | wos000655246800008&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 | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE/IET Electronic Library (IEL) customDbUrl: eissn: 1941-0042 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014516 issn: 1057-7149 databaseCode: RIE dateStart: 19920101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB508aAH17f1RQQvgnVrkybNUURRERHdw95KnrC4tuLu6t83SbtFQQUPLYWmbZiZdGbyJfMBHFGdS40pjbm2WUwYZrHkJokN59ZKF5EwG-rM3rH7-3ww4A9zcNLuhTHGhMVn5tRfBixfV2rqp8p63Pl2TrN5mGeM1nu1WsTAE84GZDNjMXNh_wySTHivf_PgEsH07BR7zCr1hUIx8bXVMP7mjQK9yu-RZvA4V93_9XUFlpvIEp3XprAKc6Zcg24TZaJmDI_XYOlLCcJ1uL15cX8U9BgIZoKW0PtQIJ-Vlmo4qhWHKovCJBV6ehVhFQcSpUZ31Uf8KMpn5AnVRuMN6F9d9i-u44ZfIVaYsIk7U-XkwjF3aU3ONOFScqK5xwIxEyLNtcLKCipSbqVJDU6UcBHmmXSHoXgTOmVVmm1A2LKMS5uk0miCVS4SQwShxoWDOs8yFkFvJuZCNbXHPQXGqAg5SMILp6PC66hodBTBcfvEa11344-2617-bbtG9BHszTRZNANzXKQZdkmXpyWM4LC97YaUx0lEaaqpb-N8dMryjESwVVtA--6Z4ez8_M1dWPQ9q-do9qAzeZuafVhQ75Ph-O3A2e0gPwh2-wlpROVN |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB5RitT2AOXRNi0FI_WCRNjgRxwfqwrE0mWFYA_cIj-lVbcJ2lf_fm0nG4FEK3FIFClOYs2MMzP-7PkAvuWmUIbkeSqMYynlhKdK2Cy1QjinfETCXawzO-DDYXF_L27W4KTbC2OtjYvP7Gm4jFi-qfUiTJX1hPftImev4DWjFGfNbq0OMwiUsxHbZDzlPvBfgZKZ6I36Nz4VxGenJKBWOJQKJTRUVyPkiT-KBCv_jjWjz7nYellv38NmG1ui740xbMOarXZgq40zUTuKZzvw7lERwl246v_2_xR0Gylmop7QcixRyEsrPZ40qkO1Q3GaCt09yLiOA8nKoEH9J72V1S8UKNUmsz0YXZyPflymLcNCqgnlc3_OtZeLIMInNgU3VCglqBEBDSRcSlwYTbSTucTCKYstybT0MeaZ8ofNyQdYr-rKfgJEHGdCuQwrayjRhcwslTS3PiA0BWM8gd5KzKVuq48HEoxJGbOQTJReR2XQUdnqKIHj7omHpvLGf9ruBvl37VrRJ7C_0mTZDs1ZiRnxaVcgJkzgqLvtB1VASmRl60Vo47005gWjCXxsLKB798pwPj__zUN4czm6HpSD_vDnF3gbetnM2OzD-ny6sF9hQy_n49n0IFrvXxgG56w |
| 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=article&rft.atitle=Image+Restoration+via+Reconciliation+of+Group+Sparsity+and+Low-Rank+Models&rft.jtitle=IEEE+transactions+on+image+processing&rft.au=Zha%2C+Zhiyuan&rft.au=Wen%2C+Bihan&rft.au=Yuan%2C+Xin&rft.au=Zhou%2C+Jiantao&rft.date=2021-01-01&rft.issn=1057-7149&rft.eissn=1941-0042&rft.volume=30&rft.spage=5223&rft.epage=5238&rft_id=info:doi/10.1109%2FTIP.2021.3078329&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TIP_2021_3078329 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1057-7149&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1057-7149&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1057-7149&client=summon |