Image Reconstruction via Manifold Constrained Convolutional Sparse Coding for Image Sets

Convolution sparse coding (CSC) has attracted much attention recently due to its advantages in image reconstruction and enhancement. However, the coding process suffers from perturbations caused by variations of input samples, as the consistence of features from similar input samples are not well ad...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE journal of selected topics in signal processing Vol. 11; no. 7; pp. 1072 - 1081
Main Authors:	Yang, Linlin, Li, Ce, Han, Jungong, Chen, Chen, Ye, Qixiang, Zhang, Baochang, Cao, Xianbin, Liu, Wanquan
Format:	Journal Article
Language:	English
Published:	New York IEEE 01.10.2017 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Constraints Convolution Convolutional codes Convolutional sparse coding Data structures Feature extraction Image coding image deblurring Image enhancement Image reconstruction Image restoration light field Light fields manifold constrained convolutional sparse coding Manifolds Robustness (mathematics) State of the art
ISSN:	1932-4553, 1941-0484
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Convolution sparse coding (CSC) has attracted much attention recently due to its advantages in image reconstruction and enhancement. However, the coding process suffers from perturbations caused by variations of input samples, as the consistence of features from similar input samples are not well addressed in the existing literature. In this paper, we will tackle this feature consistence problem from a set of samples via a proposed manifold constrained convolutional sparse coding (MCSC) method. The core idea of MCSC is to use the intrinsic manifold (Laplacian) structure of the input data to regularize the traditional CSC such that the consistence between features extracted from input samples can be well preserved. To implement the proposed MCSC method efficiently, the alternating direction method of multipliers (ADMM) approach is employed, which can consistently integrate the underlying Laplacian constraints during the optimization process. With this regularized data structure constraint, the MCSC can achieve a much better solution which is robust to the variance of the input samples against overcomplete filters. We demonstrate the capacity of MCSC by providing the state-of-the-art results when applied it to the task of reconstructing light fields. Finally, we show that the proposed MCSC is a generic approach as it also achieves better results than the state-of-the-art approaches based on convolutional sparse coding in other image reconstruction tasks, such as face reconstruction, digit reconstruction, and image restoration.
AbstractList	Convolution sparse coding (CSC) has attracted much attention recently due to its advantages in image reconstruction and enhancement. However, the coding process suffers from perturbations caused by variations of input samples, as the consistence of features from similar input samples are not well addressed in the existing literature. In this paper, we will tackle this feature consistence problem from a set of samples via a proposed manifold constrained convolutional sparse coding (MCSC) method. The core idea of MCSC is to use the intrinsic manifold (Laplacian) structure of the input data to regularize the traditional CSC such that the consistence between features extracted from input samples can be well preserved. To implement the proposed MCSC method efficiently, the alternating direction method of multipliers (ADMM) approach is employed, which can consistently integrate the underlying Laplacian constraints during the optimization process. With this regularized data structure constraint, the MCSC can achieve a much better solution which is robust to the variance of the input samples against overcomplete filters. We demonstrate the capacity of MCSC by providing the state-of-the-art results when applied it to the task of reconstructing light fields. Finally, we show that the proposed MCSC is a generic approach as it also achieves better results than the state-of-the-art approaches based on convolutional sparse coding in other image reconstruction tasks, such as face reconstruction, digit reconstruction, and image restoration.
Author	Chen Chen Baochang Zhang Xianbin Cao Ce Li Qixiang Ye Jungong Han Linlin Yang Wanquan Liu
Author_xml	– sequence: 1 givenname: Linlin surname: Yang fullname: Yang, Linlin – sequence: 2 givenname: Ce surname: Li fullname: Li, Ce – sequence: 3 givenname: Jungong surname: Han fullname: Han, Jungong – sequence: 4 givenname: Chen surname: Chen fullname: Chen, Chen – sequence: 5 givenname: Qixiang surname: Ye fullname: Ye, Qixiang – sequence: 6 givenname: Baochang surname: Zhang fullname: Zhang, Baochang – sequence: 7 givenname: Xianbin surname: Cao fullname: Cao, Xianbin – sequence: 8 givenname: Wanquan surname: Liu fullname: Liu, Wanquan
BookMark	eNp9kE1Lw0AQhhdRsK3-Ab0EPKfud3aPUvyoVBRTwVvYbCclJc3W3aTgvzdpigcPnmaYeZ9h3neMTmtXA0JXBE8Jwfr2OV2mb1OKSTKlCWdSsRM0IpqTGHPFT_ue0ZgLwc7ROIQNxiKRhI_Q53xr1hC9g3V1aHxrm9LV0b400Yupy8JVq2h22JiyhkO_d1Xbi0wVpTvjA3TDVVmvo8L5aLiWQhMu0FlhqgCXxzpBHw_3y9lTvHh9nM_uFrGlWjSxYUZIa22SY2xBSw3WGGpkTmgC2OJccKuUFUVOQHFdEJlLKUieJ8poDgmboJvh7s67rxZCk21c67vvQka0kJwyRWSnUoPKeheChyKzZWN6G72zKiM463PMDjlmfY7ZMccOpX_QnS-3xn__D10PUAkAv4DCRHS-2A-2p4Hl
CODEN	IJSTGY
CitedBy_id	crossref_primary_10_1016_j_patcog_2024_110443 crossref_primary_10_1109_TGRS_2018_2864750 crossref_primary_10_1007_s11263_022_01700_x crossref_primary_10_1007_s11042_023_15860_6 crossref_primary_10_1007_s41095_021_0259_z crossref_primary_10_1109_JSTARS_2020_3028774 crossref_primary_10_1007_s11554_018_0758_z crossref_primary_10_1109_ACCESS_2020_3003254 crossref_primary_10_1109_ACCESS_2019_2893277 crossref_primary_10_1016_j_dsp_2023_104139 crossref_primary_10_1016_j_asoc_2022_109130 crossref_primary_10_1109_JSTSP_2018_2877497 crossref_primary_10_1016_j_patcog_2017_12_023 crossref_primary_10_1007_s11042_018_6071_9 crossref_primary_10_1007_s11063_018_9871_z crossref_primary_10_3390_electronics10233021 crossref_primary_10_1109_TIP_2020_2985875 crossref_primary_10_1002_wics_1646 crossref_primary_10_1016_j_knosys_2022_110185 crossref_primary_10_1016_j_apm_2025_116382 crossref_primary_10_1109_ACCESS_2020_2999457
Cites_doi	10.1109/ICCV.2011.6126474 10.1126/science.290.5500.2323 10.1109/TCSVT.2016.2540978 10.1117/2.1201008.003113 10.1007/978-3-319-48896-7_67 10.1109/SSIAI.2016.7459193 10.1109/TIP.2014.2323127 10.1109/34.927464 10.1111/cgf.12819 10.1109/CVPR.2013.57 10.1364/OE.22.026338 10.1007/s11263-016-0880-y 10.1109/TSMC.2016.2629509 10.1111/j.1467-9868.2005.00503.x 10.1109/CVPR.2015.7298717 10.1117/12.940766 10.1145/2682631 10.1145/2461912.2461914 10.1109/CVPR.2015.7299086 10.1109/CVPR.2010.5539943 10.1109/34.291440 10.1109/TIP.2017.2718189 10.1109/TIP.2012.2210237 10.1109/ICIP.2016.7532579 10.1561/2400000003 10.1016/0024-3795(79)90089-2 10.1109/TPAMI.2013.2295311 10.1109/CVPR.2015.7299149 10.1109/CVPR.2014.394 10.1109/CVPR.2010.5539957 10.1109/CVPR.2013.465 10.1109/IVMSPW.2016.7528229 10.1111/cgf.13086 10.1109/TPAMI.2014.2388226 10.1109/ICCV.2015.212 10.1561/2200000016 10.1109/MLSP.2015.7324332
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2017
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2017
DBID	97E RIA RIE AAYXX CITATION 7SP 8FD H8D L7M
DOI	10.1109/JSTSP.2017.2743683
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library CrossRef Electronics & Communications Abstracts Technology Research Database Aerospace Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Aerospace Database Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Aerospace Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE/IET Electronic Library url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1941-0484
EndPage	1081
ExternalDocumentID	10_1109_JSTSP_2017_2743683 8015127
Genre	orig-research
GrantInformation_xml	– fundername: Beijing Municipal Science and Technology Commission grantid: Z161100001616005 – fundername: Natural Science Foundation of China grantid: 61672079; 61601466; 61473086 funderid: 10.13039/501100001809
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL RIA RIE RNS AAYXX CITATION 7SP 8FD H8D L7M RIG
ID	FETCH-LOGICAL-c295t-a3a56ccc7b00ce969ecaa2a6b127e0c0b54c88c5fb1e849f16b6651bb78a94e73
IEDL.DBID	RIE
ISICitedReferencesCount	26
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000413944400012&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1932-4553
IngestDate	Mon Jun 30 10:19:20 EDT 2025 Sat Nov 29 04:10:31 EST 2025 Tue Nov 18 21:51:28 EST 2025 Tue Aug 26 16:43:25 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	7
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c295t-a3a56ccc7b00ce969ecaa2a6b127e0c0b54c88c5fb1e849f16b6651bb78a94e73
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
PQID	1956423816
PQPubID	75721
PageCount	10
ParticipantIDs	proquest_journals_1956423816 crossref_citationtrail_10_1109_JSTSP_2017_2743683 crossref_primary_10_1109_JSTSP_2017_2743683 ieee_primary_8015127
PublicationCentury	2000
PublicationDate	2017-10-01
PublicationDateYYYYMMDD	2017-10-01
PublicationDate_xml	– month: 10 year: 2017 text: 2017-10-01 day: 01
PublicationDecade	2010
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE journal of selected topics in signal processing
PublicationTitleAbbrev	JSTSP
PublicationYear	2017
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	ref35 ref13 ref34 ref12 ref15 ref14 ref31 ref30 ref33 ref11 ref32 ref10 ref39 ref17 ref38 ref19 ref18 belkin (ref4) 0; 14 marwah (ref1) 2013; 32 mairal (ref37) 2010; 11 andilla (ref16) 2014 roweis (ref3) 2000; 290 ref24 ref23 ref26 ref25 ref20 ref42 ref41 ref22 ref21 belkin (ref5) 2006; 7 shi (ref2) 2014; 34 ref28 ref27 adams (ref36) 2008 ref29 ref8 ref7 ref9 ref6 ref40
References_xml	– ident: ref10 doi: 10.1109/ICCV.2011.6126474 – volume: 290 start-page: 2323 year: 2000 ident: ref3 article-title: Nonlinear dimensionality reduction by locally linear embedding publication-title: Science doi: 10.1126/science.290.5500.2323 – ident: ref42 doi: 10.1109/TCSVT.2016.2540978 – year: 2008 ident: ref36 article-title: Stanford light field archive – ident: ref27 doi: 10.1117/2.1201008.003113 – ident: ref31 doi: 10.1007/978-3-319-48896-7_67 – ident: ref20 doi: 10.1109/SSIAI.2016.7459193 – volume: 7 start-page: 2399 year: 2006 ident: ref5 article-title: Manifold regularization: A geometric framework for learning from labeled and unlabeled examples publication-title: J Mach Learn Res – volume: 11 start-page: 19 year: 2010 ident: ref37 article-title: Online learning for matrix factorization and sparse coding publication-title: J Mach Learn Res – ident: ref38 doi: 10.1109/TIP.2014.2323127 – ident: ref33 doi: 10.1109/34.927464 – ident: ref18 doi: 10.1111/cgf.12819 – ident: ref26 doi: 10.1109/CVPR.2013.57 – ident: ref19 doi: 10.1364/OE.22.026338 – ident: ref39 doi: 10.1007/s11263-016-0880-y – start-page: 64 year: 2014 ident: ref16 article-title: Sparse space-time deconvolution for calcium image analysis publication-title: Adv Neural Inf Process Syst – ident: ref41 doi: 10.1109/TSMC.2016.2629509 – ident: ref30 doi: 10.1111/j.1467-9868.2005.00503.x – ident: ref7 doi: 10.1109/CVPR.2015.7298717 – ident: ref29 doi: 10.1117/12.940766 – volume: 34 year: 2014 ident: ref2 article-title: Light field reconstruction using sparsity in the continuous fourier domain publication-title: ACM Trans Graph doi: 10.1145/2682631 – volume: 32 year: 2013 ident: ref1 article-title: Compressive light field photography using overcomplete dictionaries and optimized projections publication-title: ACM Trans Graph doi: 10.1145/2461912.2461914 – ident: ref6 doi: 10.1109/CVPR.2015.7299086 – ident: ref21 doi: 10.1109/CVPR.2010.5539943 – ident: ref34 doi: 10.1109/34.291440 – ident: ref40 doi: 10.1109/TIP.2017.2718189 – ident: ref28 doi: 10.1109/TIP.2012.2210237 – ident: ref22 doi: 10.1109/ICIP.2016.7532579 – ident: ref25 doi: 10.1561/2400000003 – ident: ref32 doi: 10.1016/0024-3795(79)90089-2 – ident: ref14 doi: 10.1109/TPAMI.2013.2295311 – ident: ref8 doi: 10.1109/CVPR.2015.7299149 – ident: ref11 doi: 10.1109/CVPR.2014.394 – ident: ref12 doi: 10.1109/CVPR.2010.5539957 – ident: ref9 doi: 10.1109/CVPR.2013.465 – ident: ref17 doi: 10.1109/IVMSPW.2016.7528229 – ident: ref23 doi: 10.1111/cgf.13086 – ident: ref35 doi: 10.1109/TPAMI.2014.2388226 – ident: ref13 doi: 10.1109/ICCV.2015.212 – ident: ref24 doi: 10.1561/2200000016 – volume: 14 start-page: 585 year: 0 ident: ref4 article-title: Laplacian eigenmaps and spectral techniques for embedding and clustering publication-title: Proc Int Conf Neural Inf Process – ident: ref15 doi: 10.1109/MLSP.2015.7324332
SSID	ssj0057614
Score	2.3475509
Snippet	Convolution sparse coding (CSC) has attracted much attention recently due to its advantages in image reconstruction and enhancement. However, the coding...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1072
SubjectTerms	Constraints Convolution Convolutional codes Convolutional sparse coding Data structures Feature extraction Image coding image deblurring Image enhancement Image reconstruction Image restoration light field Light fields manifold constrained convolutional sparse coding Manifolds Robustness (mathematics) State of the art
Title	Image Reconstruction via Manifold Constrained Convolutional Sparse Coding for Image Sets
URI	https://ieeexplore.ieee.org/document/8015127 https://www.proquest.com/docview/1956423816
Volume	11
WOSCitedRecordID	wos000413944400012&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 customDbUrl: eissn: 1941-0484 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0057614 issn: 1932-4553 databaseCode: RIE dateStart: 20070101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFH9sw4Me_JridEoP3rRbP9KkOcpw6MExmMJuJUkTGMxuuLm_35e0nYoieAttXkjze3kfTd57ANdoNcSS5TZvq-E-EanxuQ45AoL-FjcizqVwxSbYaJROp3zcgNttLIzW2l0-0z3bdGf5-UK9219lfZSmqJ9YE5qM0TJWq5a6aDaH1Qly5JMkiesAmYD3kcUnY3uLi_XQB4tpGn9TQq6qyg9R7PTL8OB_MzuE_cqO9O5K4I-goYtj2PuSXbAN08dXFBaedTA_08R6m5nwnkQxM4t57g3cG4E0rr2p-BAHnizR49X40Oo2Dy1brxxtoterE3gZ3j8PHvyqkIKvIp6sfRGLhCqlGO4xpTnlWgkRCSpxyjpQgUyISlOVGBnqlHATUklpEkrJUsGJZvEptIpFoc_AM7mtdIVmWMQoCQ2ROVHcHr1GgSJKkA6E9cpmqsoybr9jnjlvI-CZQyOzaGQVGh242dIsyxwbf_Zu2_Xf9qyWvgPdGsCs2oarzAZDEmuU0PPfqS5g145d3s7rQgvB0Jewozbr2ertynHYB57Yze4
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dT8IwEL8gmqgPfhtR1D34poN9dN36aIgEIhASMOFtabsuIcFBBPn7vXYbajQmvjVb23X9tffR690B3KHU4Isw0XFbU2YTHqU2Uy5DQFDfYin3E8FNsolwMIgmEzaswMPGF0YpZS6fqYYuGlt-Mpfv-qisidQU-VO4Bdsmc1burVXSXRSc3cKG7NkkCPzSRcZhTVzko6G-xxU2UAvzaeR_Y0Mmr8oPYmw4TPvwf2M7goNCkrQec-iPoaKyE9j_El_wFCbdVyQXllYxPwPFWuspt_o8m6bzWWK1zBuObUx5XaxE7Hi0QJ1X4UPN3SyUba28t5FaLc_gpf00bnXsIpWCLT0WrGzu84BKKUPcZVIxypTk3ONU4JCVIx0REBlFMkiFqyLCUpcKSgNXiDDijKjQP4dqNs_UBVhponNdoSDmhZS4KREJkUwbXz1HEslJDdxyZmNZxBnX_zGLjb7hsNigEWs04gKNGtxv2izyKBt_1j7V87-pWUx9DeolgHGxEZexdockWiyhl7-3uoXdzrjfi3vdwfMV7Onv5Hf16lBFYNQ17Mj1arp8uzGr7QOM-tE7
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+Reconstruction+via+Manifold+Constrained+Convolutional+Sparse+Coding+for+Image+Sets&rft.jtitle=IEEE+journal+of+selected+topics+in+signal+processing&rft.au=Linlin+Yang&rft.au=Ce+Li&rft.au=Jungong+Han&rft.au=Chen+Chen&rft.date=2017-10-01&rft.pub=IEEE&rft.issn=1932-4553&rft.volume=11&rft.issue=7&rft.spage=1072&rft.epage=1081&rft_id=info:doi/10.1109%2FJSTSP.2017.2743683&rft.externalDocID=8015127
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1932-4553&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1932-4553&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1932-4553&client=summon