SVTSR: Image Super-Resolution Using Scattering Vision Transformer

SVTSR: Image Super-Resolution Using Scattering Vision Transformer | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article SVTSR: Image Super-Resolution Using Scattering Vision Transformer Jiabao Liang, Yutao Jin, Xiaoyan Chen, Haotian Huang, Yue Deng This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4853264/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 30 Dec, 2024 Read the published version in Scientific Reports → Version 1 posted 11 You are reading this latest preprint version Abstract Vision transformers have garnered substantial attention and attained impressive performance in image super-resolution tasks. Nevertheless, these networks face challenges associated with attention complexity and the effective capture of intricate, fine-grained details within images. These hurdles impede the efficient and scalable deployment of transformer models for image super-resolution tasks in real-world applications. In this paper, we present a novel vision transformer called Scattering Vision Transformer for Super-Resolution (SVTSR) to tackle these challenges. SVTSR integrates a spectrally scattering network to efficiently capture intricate image details. It addresses the invertibility problem commonly encountered in down-sampling operations by separating low-frequency and high-frequency components. Additionally, SVTSR introduces a novel spectral gating network that utilizes Einstein multiplication for token and channel mixing, effectively reducing complexity. Extensive experiments show the effectiveness of the proposed vision transformer for image super-resolution tasks. Our comprehensive methodology not only outperforms state-of-the-art methods in terms of the PSNR and SSIM metrics but, more significantly, entails a reduction in model parameters exceeding tenfold when compared to the baseline model. As shown in Fig. 1, the substantial decrease of parameter amount proves highly advantageous for the deployment and practical application of super-resolution models. Code is available at https://github.com/LiangJiabaoY/SVTSR.git . Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Software Single Image Super-Resolution Dual-time Complex Wavelet Transforms Einstein Blending Method Tensor Blending Method Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 30 Dec, 2024 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 28 Oct, 2024 Reviews received at journal 20 Oct, 2024 Reviewers agreed at journal 08 Oct, 2024 Reviews received at journal 21 Sep, 2024 Reviewers agreed at journal 14 Aug, 2024 Reviewers agreed at journal 14 Aug, 2024 Reviewers invited by journal 14 Aug, 2024 Editor assigned by journal 14 Aug, 2024 Editor invited by journal 14 Aug, 2024 Submission checks completed at journal 12 Aug, 2024 First submitted to journal 03 Aug, 2024 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4853264","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":350010038,"identity":"b3a095b5-d4a4-48c4-9476-b40fcfad1412","order_by":0,"name":"Jiabao Liang","email":"","orcid":"","institution":"Tianjin University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Jiabao","middleName":"","lastName":"Liang","suffix":""},{"id":350010039,"identity":"799eebf9-07c3-4de3-b504-b197d4d80f46","order_by":1,"name":"Yutao Jin","email":"","orcid":"","institution":"Tianjin University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Yutao","middleName":"","lastName":"Jin","suffix":""},{"id":350010040,"identity":"7c1db17e-6926-497c-9dd3-932f446b0d20","order_by":2,"name":"Xiaoyan Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAy0lEQVRIie3NsQrCMBCA4ZOAOqRmPRF8hoDQRfFZhIAuznUTJycfIOJjuDpcCTiVZg3ooIuzow6CFcXRxk0wP4TLcB8HEAr9br3XrPqTIQKw74j5ggg9jlvRxk6ltQTnxIBYzT4TzLK4qU87lE5BRecGcE+fiawtYnemB2HAorkBiYMSwnjsBpSjtAbYzYs8rxBKUsAqPgSz7eSqSTWXTsl0kY84uhIitFp3OPVFw6bHwyXptoUuIQB1+f5S8XjZflHt4LEUCoVCf90dQvFB2k0DBAIAAAAASUVORK5CYII=","orcid":"","institution":"Tianjin University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Xiaoyan","middleName":"","lastName":"Chen","suffix":""},{"id":350010041,"identity":"496baf11-6eb7-4725-9817-08163c9eeef8","order_by":3,"name":"Haotian Huang","email":"","orcid":"","institution":"Tianjin University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Haotian","middleName":"","lastName":"Huang","suffix":""},{"id":350010042,"identity":"e876c13d-9ff6-4f7d-b5e9-bdf531430508","order_by":4,"name":"Yue Deng","email":"","orcid":"","institution":"Tianjin University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Yue","middleName":"","lastName":"Deng","suffix":""}],"badges":[],"createdAt":"2024-08-03 12:14:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4853264/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4853264/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-024-82650-x","type":"published","date":"2024-12-30T15:57:45+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":73093418,"identity":"32684c21-d90a-42f1-9ce5-c76da9ddcdbd","added_by":"auto","created_at":"2025-01-06 16:17:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1002970,"visible":true,"origin":"","legend":"","description":"","filename":"SVTSR.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4853264/v1_covered_d8a95395-d474-40fa-be2c-a5929fe3b007.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"SVTSR: Image Super-Resolution Using Scattering Vision Transformer","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Single Image Super-Resolution, Dual-time Complex Wavelet Transforms, Einstein Blending Method, Tensor Blending Method","lastPublishedDoi":"10.21203/rs.3.rs-4853264/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4853264/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Vision transformers have garnered substantial attention and attained impressive performance in image super-resolution tasks. Nevertheless, these networks face challenges associated with attention complexity and the effective capture of intricate, fine-grained details within images. These hurdles impede the efficient and scalable deployment of transformer models for image super-resolution tasks in real-world applications. In this paper, we present a novel vision transformer called Scattering Vision Transformer for Super-Resolution (SVTSR) to tackle these challenges. SVTSR integrates a spectrally scattering network to efficiently capture intricate image details. It addresses the invertibility problem commonly encountered in down-sampling operations by separating low-frequency and high-frequency components. Additionally, SVTSR introduces a novel spectral gating network that utilizes Einstein multiplication for token and channel mixing, effectively reducing complexity. Extensive experiments show the effectiveness of the proposed vision transformer for image super-resolution tasks. Our comprehensive methodology not only outperforms state-of-the-art methods in terms of the PSNR and SSIM metrics but, more significantly, entails a reduction in model parameters exceeding tenfold when compared to the baseline model. As shown in Fig. 1, the substantial decrease of parameter amount proves highly advantageous for the deployment and practical application of super-resolution models. Code is available at https://github.com/LiangJiabaoY/SVTSR.git.","manuscriptTitle":"SVTSR: Image Super-Resolution Using Scattering Vision Transformer","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-10-08 00:45:32","doi":"10.21203/rs.3.rs-4853264/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-10-28T11:27:55+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-10-21T00:56:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"52866690142649907329595734901268711626","date":"2024-10-08T15:12:19+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-21T13:21:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"313081060656759973045631013515251448681","date":"2024-08-14T12:27:15+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"124709536410551866373054819098891872805","date":"2024-08-14T11:47:00+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-08-14T11:42:54+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-08-14T07:56:21+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-08-14T07:43:14+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-08-12T09:58:43+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-08-03T12:12:33+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"66a1319b-fe00-4393-8463-52b0cb82c62d","owner":[],"postedDate":"October 8th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":37152450,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":37152451,"name":"Physical sciences/Mathematics and computing/Software"}],"tags":[],"updatedAt":"2025-01-06T16:03:24+00:00","versionOfRecord":{"articleIdentity":"rs-4853264","link":"https://doi.org/10.1038/s41598-024-82650-x","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2024-12-30 15:57:45","publishedOnDateReadable":"December 30th, 2024"},"versionCreatedAt":"2024-10-08 00:45:32","video":"","vorDoi":"10.1038/s41598-024-82650-x","vorDoiUrl":"https://doi.org/10.1038/s41598-024-82650-x","workflowStages":[]},"version":"v1","identity":"rs-4853264","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4853264","identity":"rs-4853264","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}