A Generalized Tensor Formulation for Hyperspectral Image Super-Resolution Under General Spatial Blurring
Hyperspectral super-resolution is commonly accomplished by the fusing of a hyperspectral imaging of low spatial resolution with a multispectral image of high spatial resolution, and many tensor-based approaches to this task have been recently proposed. Yet, it is assumed in such tensor-based methods...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence Jg. 47; H. 6; S. 4684 - 4698 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
United States
IEEE
01.06.2025
|
| Schlagworte: | |
| ISSN: | 0162-8828, 1939-3539, 2160-9292, 1939-3539 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Hyperspectral super-resolution is commonly accomplished by the fusing of a hyperspectral imaging of low spatial resolution with a multispectral image of high spatial resolution, and many tensor-based approaches to this task have been recently proposed. Yet, it is assumed in such tensor-based methods that the spatial-blurring operation that creates the observed hyperspectral image from the desired super-resolved image is separable into independent horizontal and vertical blurring. Recent work has argued that such separable spatial degradation is ill-equipped to model the operation of real sensors which may exhibit, for example, anisotropic blurring. To accommodate this fact, a generalized tensor formulation based on a Kronecker decomposition is proposed to handle any general spatial-degradation matrix, including those that are not separable as previously assumed. Analysis of the generalized formulation reveals conditions under which exact recovery of the desired super-resolved image is guaranteed, and a practical algorithm for such recovery, driven by a blockwise-group-sparsity regularization, is proposed. Extensive experimental results demonstrate that the proposed generalized tensor approach outperforms not only traditional matrix-based techniques but also state-of-the-art tensor-based methods; the gains with respect to the latter are especially significant in cases of anisotropic spatial blurring. |
|---|---|
| AbstractList | Hyperspectral super-resolution is commonly accomplished by the fusing of a hyperspectral imaging of low spatial resolution with a multispectral image of high spatial resolution, and many tensor-based approaches to this task have been recently proposed. Yet, it is assumed in such tensor-based methods that the spatial-blurring operation that creates the observed hyperspectral image from the desired super-resolved image is separable into independent horizontal and vertical blurring. Recent work has argued that such separable spatial degradation is ill-equipped to model the operation of real sensors which may exhibit, for example, anisotropic blurring. To accommodate this fact, a generalized tensor formulation based on a Kronecker decomposition is proposed to handle any general spatial-degradation matrix, including those that are not separable as previously assumed. Analysis of the generalized formulation reveals conditions under which exact recovery of the desired super-resolved image is guaranteed, and a practical algorithm for such recovery, driven by a blockwise-group-sparsity regularization, is proposed. Extensive experimental results demonstrate that the proposed generalized tensor approach outperforms not only traditional matrix-based techniques but also state-of-the-art tensor-based methods; the gains with respect to the latter are especially significant in cases of anisotropic spatial blurring. Hyperspectral super-resolution is commonly accomplished by the fusing of a hyperspectral imaging of low spatial resolution with a multispectral image of high spatial resolution, and many tensor-based approaches to this task have been recently proposed. Yet, it is assumed in such tensor-based methods that the spatial-blurring operation that creates the observed hyperspectral image from the desired super-resolved image is separable into independent horizontal and vertical blurring. Recent work has argued that such separable spatial degradation is ill-equipped to model the operation of real sensors which may exhibit, for example, anisotropic blurring. To accommodate this fact, a generalized tensor formulation based on a Kronecker decomposition is proposed to handle any general spatial-degradation matrix, including those that are not separable as previously assumed. Analysis of the generalized formulation reveals conditions under which exact recovery of the desired super-resolved image is guaranteed, and a practical algorithm for such recovery, driven by a blockwise-group-sparsity regularization, is proposed. Extensive experimental results demonstrate that the proposed generalized tensor approach outperforms not only traditional matrix-based techniques but also state-of-the-art tensor-based methods; the gains with respect to the latter are especially significant in cases of anisotropic spatial blurring.Hyperspectral super-resolution is commonly accomplished by the fusing of a hyperspectral imaging of low spatial resolution with a multispectral image of high spatial resolution, and many tensor-based approaches to this task have been recently proposed. Yet, it is assumed in such tensor-based methods that the spatial-blurring operation that creates the observed hyperspectral image from the desired super-resolved image is separable into independent horizontal and vertical blurring. Recent work has argued that such separable spatial degradation is ill-equipped to model the operation of real sensors which may exhibit, for example, anisotropic blurring. To accommodate this fact, a generalized tensor formulation based on a Kronecker decomposition is proposed to handle any general spatial-degradation matrix, including those that are not separable as previously assumed. Analysis of the generalized formulation reveals conditions under which exact recovery of the desired super-resolved image is guaranteed, and a practical algorithm for such recovery, driven by a blockwise-group-sparsity regularization, is proposed. Extensive experimental results demonstrate that the proposed generalized tensor approach outperforms not only traditional matrix-based techniques but also state-of-the-art tensor-based methods; the gains with respect to the latter are especially significant in cases of anisotropic spatial blurring. |
| Author | Li, Wei Gui, Yuanyuan Wang, Yinjian Fowler, James E. Du, Qian |
| Author_xml | – sequence: 1 givenname: Yinjian surname: Wang fullname: Wang, Yinjian email: yinjw@bit.edu.cn organization: School of Information and Electronics, Beijing Institute of Technology, and Beijing Key Laboratory of Fractional Signals and Systems, Beijing, China – sequence: 2 givenname: Wei orcidid: 0000-0001-7015-7335 surname: Li fullname: Li, Wei email: liwei089@ieee.org organization: School of Information and Electronics, Beijing Institute of Technology, and Beijing Key Laboratory of Fractional Signals and Systems, Beijing, China – sequence: 3 givenname: Yuanyuan surname: Gui fullname: Gui, Yuanyuan email: 953647315@qq.com organization: School of Information and Electronics, Beijing Institute of Technology, and Beijing Key Laboratory of Fractional Signals and Systems, Beijing, China – sequence: 4 givenname: Qian orcidid: 0000-0001-8354-7500 surname: Du fullname: Du, Qian email: du@ece.msstate.edu organization: Department of Electrical and Computer Engineering, Mississippi State University, Starkville, MS, USA – sequence: 5 givenname: James E. orcidid: 0000-0003-2005-405X surname: Fowler fullname: Fowler, James E. email: fowler@ece.msstate.edu organization: Department of Electrical and Computer Engineering, Mississippi State University, Starkville, MS, USA |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/40031662$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kUtPwzAQhC1UBG3hDyCEcuSSsrYTNzmWij4kEIi2Z8t1NiUoL-zkUH497ktCHLh4beub0WqmRzplVSIhNxQGlEL8sHwbvcwHDFg44GEQCgjPSJdRAX7MYtYhXaCC-VHEokvSs_YTgAYh8AtyGQBwKgTrko-RN8USjcqzb0y8JZa2Mt6kMkWbqyarSi9179m2RmNr1I0DvXmhNugtWvfnv6Ot8nYPrsoEzcnNW9RO7uZj3hqTlZsrcp6q3OL1cfbJavK0HM_859fpfDx69jVnQeNOyjVFQflaaCGGKQ-Ai0hFaxanGKYhuqtmIgnCBEDBmouhcqCIRcD0kPI-uT_41qb6atE2ssisxjxXJVatlZwO95aMO_TuiLbrAhNZm6xQZitP6TggOgDaVNYaTKXOmn0qLocslxTkrgi5L0LuipDHIpyU_ZGe3P8V3R5EGSL-EsTgVhL8B11BlAU |
| CODEN | ITPIDJ |
| CitedBy_id | crossref_primary_10_1109_TGRS_2025_3604437 crossref_primary_10_1109_TIP_2025_3568745 |
| Cites_doi | 10.1109/TGRS.2020.2992788 10.1109/JSTSP.2020.3045965 10.1109/CVPR.2014.377 10.1109/TIP.2016.2542360 10.1109/TIP.2021.3061908 10.1117/12.2278004 10.1109/TPAMI.2023.3279050 10.1109/TNNLS.2019.2957527 10.1137/070690729 10.1109/TGRS.2021.3114197 10.1007/978-3-319-10584-0_5 10.1109/TNNLS.2019.2956153 10.1109/TSP.2022.3201330 10.1109/TGRS.2020.3049014 10.1109/TCYB.2019.2910151 10.1109/TGRS.2016.2598784 10.1109/TIP.2020.2968773 10.1109/TGRS.2023.3315970 10.1109/TSP.2018.2876362 10.1109/TSP.2020.2965305 10.1109/TIP.2018.2855418 10.1109/TCYB.2019.2951572 10.1109/TIP.2020.2994411 10.1137/07070111X 10.1109/TGRS.2019.2936486 10.1117/12.2304455 10.1109/TIP.2019.2916734 10.1109/TGRS.2022.3215902 10.1109/TPAMI.2020.3015691 10.1109/TPAMI.2017.2734888 10.1109/CVPR.2015.7298986 10.1109/TIP.2015.2458572 10.1109/TNNLS.2023.3266038 10.1109/MGRS.2016.2637824 10.1109/TGRS.2011.2161320 10.1109/TIP.2018.2836307 10.1109/TSP.2019.2946022 10.1017/9781108779302 10.1109/CVPR52688.2022.00217 10.3390/rs8010013 10.56021/9781421407944 10.1109/TPAMI.2020.3027563 10.1109/TIP.2023.3278080 10.1109/TNNLS.2020.3028772 10.1109/83.743857 10.1109/CVPR.2017.411 10.1109/TIP.2022.3224322 10.1109/ICCV.2015.409 10.1109/TIP.2021.3058590 10.1109/TGRS.2020.2987530 10.1109/TGRS.2017.2766080 10.1109/TIP.2004.829779 10.1109/TPAMI.2022.3163307 10.1109/TNNLS.2022.3181378 10.1109/CVPR.2011.5995457 10.1109/tpami.2022.3213716 10.1109/TGRS.2014.2375320 |
| ContentType | Journal Article |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7X8 |
| DOI | 10.1109/TPAMI.2025.3545605 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | 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 Xplore 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 | Engineering Computer Science |
| EISSN | 2160-9292 1939-3539 |
| EndPage | 4698 |
| ExternalDocumentID | 40031662 10_1109_TPAMI_2025_3545605 10904006 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: National Key R&D Program of China grantid: 2021YFB3900502 |
| GroupedDBID | --- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E 9M8 AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT ADRHT AENEX AETEA 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 FA8 HZ~ H~9 IBMZZ ICLAB IEDLZ IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNI RNS RXW RZB TAE TN5 UHB VH1 XJT ~02 AAYXX CITATION NPM RIG 7X8 |
| ID | FETCH-LOGICAL-c324t-c313c1e613b6c667f340368a8b29fe5f5ea8bc26d45d00a0b367ac6669642c713 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 4 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001484716600002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0162-8828 1939-3539 |
| IngestDate | Sun Sep 28 08:05:48 EDT 2025 Mon Jul 21 06:07:17 EDT 2025 Tue Nov 18 22:27:46 EST 2025 Sat Nov 29 07:54:57 EST 2025 Wed Aug 27 01:53:10 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 6 |
| 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-c324t-c313c1e613b6c667f340368a8b29fe5f5ea8bc26d45d00a0b367ac6669642c713 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0001-7015-7335 0000-0001-8354-7500 0000-0003-2005-405X |
| PMID | 40031662 |
| PQID | 3173403623 |
| PQPubID | 23479 |
| PageCount | 15 |
| ParticipantIDs | crossref_citationtrail_10_1109_TPAMI_2025_3545605 pubmed_primary_40031662 crossref_primary_10_1109_TPAMI_2025_3545605 proquest_miscellaneous_3173403623 ieee_primary_10904006 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-06-01 |
| PublicationDateYYYYMMDD | 2025-06-01 |
| PublicationDate_xml | – month: 06 year: 2025 text: 2025-06-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | IEEE transactions on pattern analysis and machine intelligence |
| PublicationTitleAbbrev | TPAMI |
| PublicationTitleAlternate | IEEE Trans Pattern Anal Mach Intell |
| PublicationYear | 2025 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| References | ref13 ref57 ref12 ref56 ref15 ref14 ref53 ref52 ref11 ref55 ref10 ref54 ref17 ref16 ref19 ref18 ref51 ref50 ref46 ref45 ref48 ref47 ref42 ref41 ref44 ref43 ref49 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref1 ref39 ref38 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref28 ref27 ref29 |
| References_xml | – ident: ref32 doi: 10.1109/TGRS.2020.2992788 – ident: ref31 doi: 10.1109/JSTSP.2020.3045965 – ident: ref49 doi: 10.1109/CVPR.2014.377 – ident: ref11 doi: 10.1109/TIP.2016.2542360 – ident: ref52 doi: 10.1109/TIP.2021.3061908 – ident: ref40 doi: 10.1117/12.2278004 – ident: ref24 doi: 10.1109/TPAMI.2023.3279050 – ident: ref34 doi: 10.1109/TNNLS.2019.2957527 – ident: ref43 doi: 10.1137/070690729 – ident: ref47 doi: 10.1109/TGRS.2021.3114197 – ident: ref10 doi: 10.1007/978-3-319-10584-0_5 – ident: ref50 doi: 10.1109/TNNLS.2019.2956153 – ident: ref54 doi: 10.1109/TSP.2022.3201330 – ident: ref17 doi: 10.1109/TGRS.2020.3049014 – ident: ref56 doi: 10.1109/TCYB.2019.2910151 – ident: ref8 doi: 10.1109/TGRS.2016.2598784 – ident: ref14 doi: 10.1109/TIP.2020.2968773 – ident: ref2 doi: 10.1109/TGRS.2023.3315970 – ident: ref28 doi: 10.1109/TSP.2018.2876362 – ident: ref30 doi: 10.1109/TSP.2020.2965305 – ident: ref12 doi: 10.1109/TIP.2018.2855418 – ident: ref46 doi: 10.1109/TCYB.2019.2951572 – ident: ref27 doi: 10.1109/TIP.2020.2994411 – ident: ref44 doi: 10.1137/07070111X – ident: ref36 doi: 10.1109/TGRS.2019.2936486 – ident: ref41 doi: 10.1117/12.2304455 – ident: ref16 doi: 10.1109/TIP.2019.2916734 – ident: ref23 doi: 10.1109/TGRS.2022.3215902 – ident: ref25 doi: 10.1109/TPAMI.2020.3015691 – ident: ref53 doi: 10.1109/TPAMI.2017.2734888 – ident: ref19 doi: 10.1109/CVPR.2015.7298986 – ident: ref20 doi: 10.1109/TIP.2015.2458572 – ident: ref35 doi: 10.1109/TNNLS.2023.3266038 – ident: ref1 doi: 10.1109/MGRS.2016.2637824 – ident: ref6 doi: 10.1109/TGRS.2011.2161320 – ident: ref29 doi: 10.1109/TIP.2018.2836307 – ident: ref55 doi: 10.1109/TSP.2019.2946022 – ident: ref57 doi: 10.1017/9781108779302 – ident: ref37 doi: 10.1109/CVPR52688.2022.00217 – ident: ref42 doi: 10.3390/rs8010013 – ident: ref45 doi: 10.56021/9781421407944 – ident: ref18 doi: 10.1109/TPAMI.2020.3027563 – ident: ref22 doi: 10.1109/TIP.2023.3278080 – ident: ref21 doi: 10.1109/TNNLS.2020.3028772 – ident: ref3 doi: 10.1109/83.743857 – ident: ref26 doi: 10.1109/CVPR.2017.411 – ident: ref38 doi: 10.1109/TIP.2022.3224322 – ident: ref7 doi: 10.1109/ICCV.2015.409 – ident: ref15 doi: 10.1109/TIP.2021.3058590 – ident: ref33 doi: 10.1109/TGRS.2020.2987530 – ident: ref9 doi: 10.1109/TGRS.2017.2766080 – ident: ref4 doi: 10.1109/TIP.2004.829779 – ident: ref39 doi: 10.1109/TPAMI.2022.3163307 – ident: ref51 doi: 10.1109/TNNLS.2022.3181378 – ident: ref5 doi: 10.1109/CVPR.2011.5995457 – ident: ref48 doi: 10.1109/tpami.2022.3213716 – ident: ref13 doi: 10.1109/TGRS.2014.2375320 |
| SSID | ssj0014503 |
| Score | 2.5116925 |
| Snippet | Hyperspectral super-resolution is commonly accomplished by the fusing of a hyperspectral imaging of low spatial resolution with a multispectral image of high... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 4684 |
| SubjectTerms | Anisotropic Degradation Hyperspectral imaging hyperspectral super-resolution Image fusion Mathematical models Matrix decomposition nonconvex surrogate Optimization recoverability sparse coding Spatial resolution Superresolution tensor factorization Tensors Vectors |
| Title | A Generalized Tensor Formulation for Hyperspectral Image Super-Resolution Under General Spatial Blurring |
| URI | https://ieeexplore.ieee.org/document/10904006 https://www.ncbi.nlm.nih.gov/pubmed/40031662 https://www.proquest.com/docview/3173403623 |
| Volume | 47 |
| WOSCitedRecordID | wos001484716600002&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 Xplore customDbUrl: eissn: 2160-9292 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB60eNCD1Vq1PsoK3iTt5rXbHKtYWtBSsEJvIdlMVNBU-vDgr3d2k5R6qOAlLGF2kzCzmfl2d-YDuEYb_YTz2IolIR0CKKkV2xFaEcckTZXtJJ5JFH6Qw2FnMglGRbK6yYVBRHP4DFu6afbyk6la6qWytj5E6JkC29tSijxZa7Vl4PmGBplCGJrihCPKDBketMej7uOAsKDjt1wdMXDNV-NpexbC-eWQDMPK5mDTOJ1e9Z-vewD7RXTJurk5HMIWZjWolswNrJjINdhbK0N4BK9dVlSffvvGhI0J2U5nrEfRbMHtxSiyZX1CrHliJgmywQf9iNjTku5ZegsgN2BmaJTK0ZjmOyb7ZrfveqExe6nDc-9-fNe3CgYGS1GgtaCr7SobyeXHQgkhU9cjj9eJOrETpOinPlJTOSLxtMIjHrtCRiQoAoI1ivDvMVSyaYanwFJOGN5xYvIN0lOJiAn4SRoChe-h5HYD7FINoSrKk2uWjPfQwBQehEaLodZiWGixATerPp95cY4_petaR2uSuXoacFWqO6S5pTdMogyny3lIsZX5YMdtwEluB6vepfmcbRj1HHb1w_NTZRdQWcyWeAk76mvxNp81yYAnnaYx4B_WSOpI |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS8MwED9kCuqD0_k1PyP4Jp3pV7o-TnFsOIfghL2VNr2qMDvZhw_-9V7SdMwHBV9KKElIuUvvfrnc_QAu0UY_5TyxkoCQDgGUzErsGK2YY5pl0nZSTycK94J-vzkcho8mWV3nwiCivnyGDdXUsfx0LOfqqOxaXSL0dIHtVUWdZdK1FkEDz9dEyOTE0CYnJFHmyPDwevDYeugSGnT8hqt8Bq4Yazyl0UI4P0yS5lj53d3UZqdd_eeCt2HL-JesVSjEDqxgXoNqyd3AzFauweZSIcJdeG0xU3_67QtTNiBsO56wNvmzht2LkW_LOoRZi9RM6si67_QrYk9zemepIEChwkwTKZWzMcV4TBrObkbqqDF_2YPn9t3gtmMZDgZLkqs1o6ftShvJ6CdCChFkrkc2rxk3EyfM0M98pKZ0ROopkcc8cUUQU0cRErCRhID3oZKPczwElnFC8Y6TkHUIPJmKhKBfQFOg8D0MuF0HuxRDJE2BcsWTMYo0UOFhpKUYKSlGRop1uFqM-SjKc_zZe0_JaKlnIZ46XJTijmh3qZBJnON4Po3Iu9If7Lh1OCj0YDG6VJ-jX2Y9h_XO4KEX9br9-2PYUAsp7pidQGU2meMprMnP2dt0cqbV-Busyuyp |
| 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=A+Generalized+Tensor+Formulation+for+Hyperspectral+Image+Super-Resolution+Under+General+Spatial+Blurring&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Wang%2C+Yinjian&rft.au=Li%2C+Wei&rft.au=Gui%2C+Yuanyuan&rft.au=Du%2C+Qian&rft.date=2025-06-01&rft.eissn=1939-3539&rft.volume=47&rft.issue=6&rft.spage=4684&rft_id=info:doi/10.1109%2FTPAMI.2025.3545605&rft_id=info%3Apmid%2F40031662&rft.externalDocID=40031662 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon |