Structural Similarity-Inspired Unfolding for Lightweight Image Super-Resolution

Major efforts in data-driven image super-resolution (SR) primarily focus on expanding the receptive field of the model to better capture contextual information. However, these methods are typically implemented by stacking deeper networks or leveraging transformer-based attention mechanisms, which co...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on image processing Vol. 34; pp. 3861 - 3872
Main Authors:	Ni, Zhangkai, Zhang, Yang, Yang, Wenhan, Wang, Hanli, Wang, Shiqi, Kwong, Sam
Format:	Journal Article
Language:	English
Published:	United States IEEE 01.01.2025
Subjects:	Complexity theory Computational modeling Electronic mail Encoding Estimation Feature extraction Image reconstruction Image super-resolution light-weight Optimization paradigm unfolding sparse attention Superresolution Transformers
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	Major efforts in data-driven image super-resolution (SR) primarily focus on expanding the receptive field of the model to better capture contextual information. However, these methods are typically implemented by stacking deeper networks or leveraging transformer-based attention mechanisms, which consequently increases model complexity. In contrast, model-driven methods based on the unfolding paradigm show promise in improving performance while effectively maintaining model compactness through sophisticated module design. Based on these insights, we propose a Structural Similarity-Inspired Unfolding (SSIU) method for efficient image SR. This method is designed through unfolding an SR optimization function constrained by structural similarity, aiming to combine the strengths of both data-driven and model-driven approaches. Our model operates progressively following the unfolding paradigm. Each iteration consists of multiple Mixed-Scale Gating Modules (MSGM) and an Efficient Sparse Attention Module (ESAM). The former implements comprehensive constraints on features, including a structural similarity constraint, while the latter aims to achieve sparse activation. In addition, we design a Mixture-of-Experts-based Feature Selector (MoE-FS) that fully utilizes multi-level feature information by combining features from different steps. Extensive experiments validate the efficacy and efficiency of our unfolding-inspired network. Our model outperforms current state-of-the-art models, boasting lower parameter counts and reduced memory consumption. Our code will be available at: https://github.com/eezkni/SSIU
AbstractList	Major efforts in data-driven image super-resolution (SR) primarily focus on expanding the receptive field of the model to better capture contextual information. However, these methods are typically implemented by stacking deeper networks or leveraging transformer-based attention mechanisms, which consequently increases model complexity. In contrast, model-driven methods based on the unfolding paradigm show promise in improving performance while effectively maintaining model compactness through sophisticated module design. Based on these insights, we propose a Structural Similarity-Inspired Unfolding (SSIU) method for efficient image SR. This method is designed through unfolding an SR optimization function constrained by structural similarity, aiming to combine the strengths of both data-driven and model-driven approaches. Our model operates progressively following the unfolding paradigm. Each iteration consists of multiple Mixed-Scale Gating Modules (MSGM) and an Efficient Sparse Attention Module (ESAM). The former implements comprehensive constraints on features, including a structural similarity constraint, while the latter aims to achieve sparse activation. In addition, we design a Mixture-of-Experts-based Feature Selector (MoE-FS) that fully utilizes multi-level feature information by combining features from different steps. Extensive experiments validate the efficacy and efficiency of our unfolding-inspired network. Our model outperforms current state-of-the-art models, boasting lower parameter counts and reduced memory consumption. Our code will be available at: https://github.com/eezkni/SSIU Major efforts in data-driven image super-resolution (SR) primarily focus on expanding the receptive field of the model to better capture contextual information. However, these methods are typically implemented by stacking deeper networks or leveraging transformer-based attention mechanisms, which consequently increases model complexity. In contrast, model-driven methods based on the unfolding paradigm show promise in improving performance while effectively maintaining model compactness through sophisticated module design. Based on these insights, we propose a Structural Similarity-Inspired Unfolding (SSIU) method for efficient image SR. This method is designed through unfolding an SR optimization function constrained by structural similarity, aiming to combine the strengths of both data-driven and model-driven approaches. Our model operates progressively following the unfolding paradigm. Each iteration consists of multiple Mixed-Scale Gating Modules (MSGM) and an Efficient Sparse Attention Module (ESAM). The former implements comprehensive constraints on features, including a structural similarity constraint, while the latter aims to achieve sparse activation. In addition, we design a Mixture-of-Experts-based Feature Selector (MoE-FS) that fully utilizes multi-level feature information by combining features from different steps. Extensive experiments validate the efficacy and efficiency of our unfolding-inspired network. Our model outperforms current state-of-the-art models, boasting lower parameter counts and reduced memory consumption. Our code will be available at: https://github.com/eezkni/SSIU.Major efforts in data-driven image super-resolution (SR) primarily focus on expanding the receptive field of the model to better capture contextual information. However, these methods are typically implemented by stacking deeper networks or leveraging transformer-based attention mechanisms, which consequently increases model complexity. In contrast, model-driven methods based on the unfolding paradigm show promise in improving performance while effectively maintaining model compactness through sophisticated module design. Based on these insights, we propose a Structural Similarity-Inspired Unfolding (SSIU) method for efficient image SR. This method is designed through unfolding an SR optimization function constrained by structural similarity, aiming to combine the strengths of both data-driven and model-driven approaches. Our model operates progressively following the unfolding paradigm. Each iteration consists of multiple Mixed-Scale Gating Modules (MSGM) and an Efficient Sparse Attention Module (ESAM). The former implements comprehensive constraints on features, including a structural similarity constraint, while the latter aims to achieve sparse activation. In addition, we design a Mixture-of-Experts-based Feature Selector (MoE-FS) that fully utilizes multi-level feature information by combining features from different steps. Extensive experiments validate the efficacy and efficiency of our unfolding-inspired network. Our model outperforms current state-of-the-art models, boasting lower parameter counts and reduced memory consumption. Our code will be available at: https://github.com/eezkni/SSIU. Major efforts in data-driven image super-resolution (SR) primarily focus on expanding the receptive field of the model to better capture contextual information. However, these methods are typically implemented by stacking deeper networks or leveraging transformer-based attention mechanisms, which consequently increases model complexity. In contrast, model-driven methods based on the unfolding paradigm show promise in improving performance while effectively maintaining model compactness through sophisticated module design. Based on these insights, we propose a Structural Similarity-Inspired Unfolding (SSIU) method for efficient image SR. This method is designed through unfolding an SR optimization function constrained by structural similarity, aiming to combine the strengths of both data-driven and model-driven approaches. Our model operates progressively following the unfolding paradigm. Each iteration consists of multiple Mixed-Scale Gating Modules (MSGM) and an Efficient Sparse Attention Module (ESAM). The former implements comprehensive constraints on features, including a structural similarity constraint, while the latter aims to achieve sparse activation. In addition, we design a Mixture-of-Experts-based Feature Selector (MoE-FS) that fully utilizes multi-level feature information by combining features from different steps. Extensive experiments validate the efficacy and efficiency of our unfolding-inspired network. Our model outperforms current state-of-the-art models, boasting lower parameter counts and reduced memory consumption. Our code will be available at: https://github.com/eezkni/SSIU.
Author	Wang, Shiqi Zhang, Yang Wang, Hanli Kwong, Sam Ni, Zhangkai Yang, Wenhan
Author_xml	– sequence: 1 givenname: Zhangkai orcidid: 0000-0003-3682-6288 surname: Ni fullname: Ni, Zhangkai email: zkni@tongji.edu.cn organization: School of Computer Science and Technology and the Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China – sequence: 2 givenname: Yang surname: Zhang fullname: Zhang, Yang email: zhangy_ce@tongji.edu.cn organization: School of Computer Science and Technology and the Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China – sequence: 3 givenname: Wenhan orcidid: 0000-0002-1692-0069 surname: Yang fullname: Yang, Wenhan email: yangwh@pcl.ac.cn organization: Pengcheng Laboratory, Shenzhen, Guangdong, China – sequence: 4 givenname: Hanli orcidid: 0000-0002-9999-4871 surname: Wang fullname: Wang, Hanli email: hanliwang@tongji.edu.cn organization: School of Computer Science and Technology and the Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China – sequence: 5 givenname: Shiqi orcidid: 0000-0002-3583-959X surname: Wang fullname: Wang, Shiqi email: shiqwang@cityu.edu.hk organization: Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong – sequence: 6 givenname: Sam orcidid: 0000-0001-7484-7261 surname: Kwong fullname: Kwong, Sam email: samkwong@ln.edu.hk organization: School of Data Science, Lingnan University, Tuen Mun, Hong Kong
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/40531647$$D View this record in MEDLINE/PubMed
BookMark	eNpFkE1Lw0AQhhep2Fq9exDJ0Uvqzn4k2aMUPwoFxdZz2Gxm60o-6m6C9N-b0qqXmYH3eefwnJNR0zZIyBXQGQBVd-vF64xRJmdcplkq-QmZgBIQUyrYaLipTOMUhBqT8xA-KQUhITkjY0Elh0SkE_Ky6nxvut7rKlq52lXau24XL5qwdR7L6L2xbVW6ZhPZ1kdLt_novnE_o0WtNxit-i36-A1DW_Wda5sLcmp1FfDyuKdk_fiwnj_Hy5enxfx-GRuWyi5WFGjGEoGlLiyAEMparorMmIwXqSpNohXLMFUWMaGlMoBFaWiWWWmUtnxKbg9vt7796jF0ee2CwarSDbZ9yDljjMuEcRjQmyPaFzWW-da7Wvtd_utgAOgBML4NwaP9Q4Dme835oDnfa86PmofK9aHiEPEfB8oVDPEPyEx5ZA
CODEN	IIPRE4
Cites_doi	10.1109/iccv.2001.937655 10.1109/TPAMI.2013.102 10.1007/978-3-030-01234-2_18 10.1109/ICCVW54120.2021.00210 10.1109/JBHI.2024.3454068 10.1109/TIP.2024.3368960 10.1109/TPAMI.2021.3088914 10.1109/LSP.2023.3264558 10.1109/CVPR52729.2023.02143 10.1145/3474085.3475291 10.1007/978-3-030-01249-6_16 10.1109/CVPR.2016.182 10.1109/TIP.2023.3279977 10.1109/WACV56688.2023.00493 10.1109/CVPR42600.2020.00583 10.1109/CVPR.2019.01132 10.1109/TIP.2023.3348293 10.1007/978-3-642-27413-8_47 10.24963/ijcai.2022/128 10.1109/ICCV51070.2023.01150 10.1109/ICCV51070.2023.01213 10.1109/CVPR.2016.207 10.1007/s11263-019-01285-y 10.1007/978-3-030-58610-2_12 10.1109/CVPR.2015.7299156 10.1109/TPAMI.2015.2439281 10.1109/TBC.2024.3374122 10.1109/CVPR46437.2021.00908 10.1109/CVPR.2017.298 10.1109/TIP.2022.3154614 10.1109/CVPR52733.2024.02437 10.1007/s11263-022-01699-1 10.1109/TCSVT.2024.3467259 10.1109/ICCV51070.2023.01174 10.1007/978-3-031-73661-2_27 10.1109/tcsvt.2025.3549351 10.5244/C.26.135 10.1109/CVPRW.2017.151 10.1016/j.patcog.2023.110095 10.1109/CVPRW.2017.150 10.1007/s11263-023-01813-x 10.1007/s11263-019-01253-6 10.1109/CVPR46437.2021.00488 10.1109/CVPR52733.2024.00276 10.1109/TIP.2012.2235847 10.1109/CVPRW56347.2022.00061 10.1109/CVPR46437.2021.00776 10.1109/TIP.2021.3050856 10.1109/CVPR52729.2023.02142 10.1109/TIP.2011.2108306 10.1002/cpa.20042 10.1145/3343031.3351084 10.1007/s11042-016-4020-z 10.1109/CVPR.2019.00177
ContentType	Journal Article
DBID	97E RIA RIE AAYXX CITATION NPM 7X8
DOI	10.1109/TIP.2025.3578753
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) CrossRef PubMed MEDLINE - Academic
DatabaseTitle	CrossRef PubMed MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic PubMed
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	3872
ExternalDocumentID	40531647 10_1109_TIP_2025_3578753 11039153
Genre	orig-research Journal Article
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 62201387; 62371343 funderid: 10.13039/501100001809 – fundername: Fundamental Research Funds for the Central Universities funderid: 10.13039/501100012226 – fundername: Interdisciplinary Frontier Research Project of Pengcheng Laboratory (PCL) grantid: 2025QYB013 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 AAYOK NPM RIG 7X8
ID	FETCH-LOGICAL-c275t-90108264edabf11449ff39b8cc83b79dc6a928e79fee60d9c1ebdc088f5c9af3
IEDL.DBID	RIE
ISICitedReferencesCount	1
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001516237300007&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	Thu Oct 02 22:33:44 EDT 2025 Thu Jun 26 01:52:28 EDT 2025 Sat Nov 29 07:51:43 EST 2025 Wed Aug 27 01:36:10 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-c275t-90108264edabf11449ff39b8cc83b79dc6a928e79fee60d9c1ebdc088f5c9af3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ORCID	0000-0002-1692-0069 0000-0002-3583-959X 0000-0001-7484-7261 0000-0002-9999-4871 0000-0003-3682-6288
PMID	40531647
PQID	3222356231
PQPubID	23479
PageCount	12
ParticipantIDs	pubmed_primary_40531647 crossref_primary_10_1109_TIP_2025_3578753 proquest_miscellaneous_3222356231 ieee_primary_11039153
PublicationCentury	2000
PublicationDate	2025-01-01
PublicationDateYYYYMMDD	2025-01-01
PublicationDate_xml	– month: 01 year: 2025 text: 2025-01-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	IEEE transactions on image processing
PublicationTitleAbbrev	TIP
PublicationTitleAlternate	IEEE Trans Image Process
PublicationYear	2025
Publisher	IEEE
Publisher_xml	– name: IEEE
References	ref13 ref12 ref56 ref15 ref59 ref14 Li (ref35); 33 ref53 ref52 ref11 ref55 ref10 ref54 ref17 ref16 ref19 ref18 ref51 ref50 ref46 Sun (ref38) ref45 ref48 ref47 Loshchilov (ref58) ref42 ref41 ref44 ref43 ref49 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref1 ref39 Kingma (ref57) ref23 ref26 ref25 ref20 ref22 ref21 ref28 ref27 ref29 Dosovitskiy (ref24)
References_xml	– ident: ref54 doi: 10.1109/iccv.2001.937655 – ident: ref46 doi: 10.1109/TPAMI.2013.102 – ident: ref4 doi: 10.1007/978-3-030-01234-2_18 – ident: ref11 doi: 10.1109/ICCVW54120.2021.00210 – ident: ref9 doi: 10.1109/JBHI.2024.3454068 – start-page: 17314 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref38 article-title: ShuffleMixer: An efficient ConvNet for image super-resolution – ident: ref8 doi: 10.1109/TIP.2024.3368960 – ident: ref17 doi: 10.1109/TPAMI.2021.3088914 – ident: ref15 doi: 10.1109/LSP.2023.3264558 – ident: ref43 doi: 10.1109/CVPR52729.2023.02143 – ident: ref36 doi: 10.1145/3474085.3475291 – ident: ref33 doi: 10.1007/978-3-030-01249-6_16 – ident: ref2 doi: 10.1109/CVPR.2016.182 – ident: ref12 doi: 10.1109/TIP.2023.3279977 – ident: ref26 doi: 10.1109/WACV56688.2023.00493 – ident: ref25 doi: 10.1109/CVPR42600.2020.00583 – ident: ref5 doi: 10.1109/CVPR.2019.01132 – ident: ref50 doi: 10.1109/TIP.2023.3348293 – ident: ref53 doi: 10.1007/978-3-642-27413-8_47 – ident: ref39 doi: 10.24963/ijcai.2022/128 – ident: ref41 doi: 10.1109/ICCV51070.2023.01150 – ident: ref42 doi: 10.1109/ICCV51070.2023.01213 – ident: ref13 doi: 10.1109/CVPR.2016.207 – start-page: 1 volume-title: Proc. Int. Conf. Learn. Represent. ident: ref58 article-title: SGDR: Stochastic gradient descent with warm restarts – ident: ref48 doi: 10.1007/s11263-019-01285-y – ident: ref6 doi: 10.1007/978-3-030-58610-2_12 – ident: ref55 doi: 10.1109/CVPR.2015.7299156 – ident: ref1 doi: 10.1109/TPAMI.2015.2439281 – ident: ref30 doi: 10.1109/TBC.2024.3374122 – ident: ref59 doi: 10.1109/CVPR46437.2021.00908 – volume: 33 start-page: 20343 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref35 article-title: LAPAR: Linearly-assembled pixel-adaptive regression network for single image super-aesolution and beyond – ident: ref22 doi: 10.1109/CVPR.2017.298 – ident: ref3 doi: 10.1109/TIP.2022.3154614 – ident: ref31 doi: 10.1109/CVPR52733.2024.02437 – ident: ref19 doi: 10.1007/s11263-022-01699-1 – ident: ref28 doi: 10.1109/TCSVT.2024.3467259 – ident: ref40 doi: 10.1109/ICCV51070.2023.01174 – ident: ref44 doi: 10.1007/978-3-031-73661-2_27 – ident: ref29 doi: 10.1109/tcsvt.2025.3549351 – ident: ref52 doi: 10.5244/C.26.135 – ident: ref32 doi: 10.1109/CVPRW.2017.151 – ident: ref23 doi: 10.1016/j.patcog.2023.110095 – ident: ref51 doi: 10.1109/CVPRW.2017.150 – ident: ref49 doi: 10.1007/s11263-023-01813-x – ident: ref14 doi: 10.1007/s11263-019-01253-6 – start-page: 1 volume-title: Proc. Int. Conf. Learn. Represent. ident: ref24 article-title: An image is worth 16×16 words: Transformers for image recognition at scale – ident: ref37 doi: 10.1109/CVPR46437.2021.00488 – ident: ref27 doi: 10.1109/CVPR52733.2024.00276 – ident: ref45 doi: 10.1109/TIP.2012.2235847 – start-page: 1 volume-title: Proc. Int. Conf. Learn. Represent. ident: ref57 article-title: Adam: A method for stochastic optimization – ident: ref10 doi: 10.1109/CVPRW56347.2022.00061 – ident: ref16 doi: 10.1109/CVPR46437.2021.00776 – ident: ref7 doi: 10.1109/TIP.2021.3050856 – ident: ref20 doi: 10.1109/CVPR52729.2023.02142 – ident: ref21 doi: 10.1109/TIP.2011.2108306 – ident: ref47 doi: 10.1002/cpa.20042 – ident: ref34 doi: 10.1145/3343031.3351084 – ident: ref56 doi: 10.1007/s11042-016-4020-z – ident: ref18 doi: 10.1109/CVPR.2019.00177
SSID	ssj0014516
Score	2.473553
Snippet	Major efforts in data-driven image super-resolution (SR) primarily focus on expanding the receptive field of the model to better capture contextual...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Publisher
StartPage	3861
SubjectTerms	Complexity theory Computational modeling Electronic mail Encoding Estimation Feature extraction Image reconstruction Image super-resolution light-weight Optimization paradigm unfolding sparse attention Superresolution Transformers
Title	Structural Similarity-Inspired Unfolding for Lightweight Image Super-Resolution
URI	https://ieeexplore.ieee.org/document/11039153 https://www.ncbi.nlm.nih.gov/pubmed/40531647 https://www.proquest.com/docview/3222356231
Volume	34
WOSCitedRecordID	wos001516237300007&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/eLvHCXMwlV1LT8JAEJ4IMQYPoviqD1ITLx4KfW_3aIxEEoIkYMKtYR9NOFAID_37zmwLcuHgrYe-Mt_s7jf77cwAPMcTznyRKZz9ROCElMTFZeA5EfOTjE8yJaWprt9j_X4yHvNBmaxucmG01ubwmW7RpdHy1VxuaKus7XmmnnlQgQpjcZGstZMMqOOskTYj5jDk_VtN0uXtUXeAkaAftai0C_LzGpyE5HwxNVXZW45Mf5XDVNMsOZ36P3_2HM5Kbmm_Fs5wAUc6b0C95Jl2OYpXDTjdK0J4CZ9DU0KWym_Yw-lsiqEuMnOnm5MGj899oQsahcpGfmv3KJj_MfupdneGk5E93Cz00iEZoHDiKxh13kdvH07ZZsGRPovW5oAGBhmhVhORYXgU8iwLuEikTALBuJKIp59oxjOtY1dx6WmhJM5OWSQRzeAaqvk817dge0mMiPtMaBZg2OeKULhKMoWhr0YmJC142Ro7XRTFNFIThLg8RYxSwigtMbLgimz6d19pTguetvCkOBJI3pjker5ZpaQZBUTnPAtuCtx2T2_hvjvw1nuo0ceLvZUHqKLh9SMcy-_1dLVsoruNk6Zxt1-in9AW
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8JAEJ4oGsWD-EDFZ028eCj0yXaPxkggIpKACbeGfTThQCE89O87sy3IhYO3Htpms9_s7vfttzML8FQfcuaJROHsJ3w7oCQuLn3XDpkXJXyYKClNdf0263SiwYB382R1kwujtTaHz3SVHo2XryZySVtlNdc19cz9XdgLg8BzsnSttWlAd84aczNkNkPmv3IlHV7rt7qoBb2wSsVdkKEX4SCg8KvTtSobC5K5YWU72TSLTqP0z-aewHHOLq2XLBxOYUenZ1DKmaaVj-P5GRxtlCE8h8-eKSJLBTis3mg8QrGL3NxupeTC43dfGITGo7KQ4VptkvM_ZkfVao1xOrJ6y6me2WQEZGFchn7jrf_atPOLFmzpsXBhjmigzAi0GooEBVLAk8TnIpIy8gXjSiKiXqQZT7SuO4pLVwslcX5KQol4-hdQSCepvgLLjeqIuceEZj4KP0cEwlGSKRS_GrmQrMDzqrPjaVZOIzYyxOExYhQTRnGOUQXK1Kd_7-XdWYHHFTwxjgUyOIapniznMblGPhE6twKXGW7rr1dwX2_56wMcNvsf7bjd6rzfQJEaku203EIBQdB3sC-_F6P57N4E3S-3X9J1
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=Structural+Similarity-Inspired+Unfolding+for+Lightweight+Image+Super-Resolution&rft.jtitle=IEEE+transactions+on+image+processing&rft.au=Ni%2C+Zhangkai&rft.au=Zhang%2C+Yang&rft.au=Yang%2C+Wenhan&rft.au=Wang%2C+Hanli&rft.date=2025-01-01&rft.issn=1057-7149&rft.eissn=1941-0042&rft.volume=34&rft.spage=3861&rft.epage=3872&rft_id=info:doi/10.1109%2FTIP.2025.3578753&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TIP_2025_3578753
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