HADT : Image Super-Resolution Restoration Using Hybrid Attention-Dense Connected Transformer Networks

HADT : Image Super-Resolution Restoration Using Hybrid Attention-Dense Connected Transformer Networks | 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 Research Article HADT : Image Super-Resolution Restoration Using Hybrid Attention-Dense Connected Transformer Networks Ying Guo, Chang Tian, Jie Liu, Chong Di, Keqing Ning This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4767541/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 3 You are reading this latest preprint version Abstract Image super-resolution (SR) plays a vital role in vision tasks, in which Transformer-based methods outperform conventional convolutional neural networks. Existing work usually uses residual linking to improve the performance, but this type of linking provides limited information transfer within the block. Also, in order to improve feature extraction, existing work usually restricts the self-attention computation to a single window. This means that transformer-based networks can only use feature information within a limited spatial range. To handle the challenge, this paper proposes a novel Hybrid Attention-Dense Connected Transformer Networks (HADT) to better utilise the potential feature information. HADT is constructed by stacking attentional transformer block (ATB), which contains Effective Dense Transformer Block (EDTB) and Hybrid Attention Block (HAB). EDTB combines dense connectivity and swin-transformer to enhance feature transfer and improve model representation, and meanwhile, HAB is used for cross-window information interaction and joint modelling of features for better visualisation. Based on the experiments, our method is effective on SR tasks with magnification factors of 2, 3, and 4. For example, using the Urban100 dataset in an experiment with an amplification factor of 4 our method has a PSNR value that is 0.15 dB higher than the previous method and reconstructs a more detailed texture. Hybrid attention transformer Image super-resolution Dense connection transformer Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editor assigned by journal 29 Jul, 2024 Submission checks completed at journal 24 Jul, 2024 First submitted to journal 19 Jul, 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-4767541","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":333083200,"identity":"b24f4d85-ad91-442e-a08d-28f891b18f9a","order_by":0,"name":"Ying Guo","email":"","orcid":"","institution":"Tsinghua University","correspondingAuthor":false,"prefix":"","firstName":"Ying","middleName":"","lastName":"Guo","suffix":""},{"id":333083201,"identity":"ceef04ce-02de-4ab5-b481-7a539fb76b56","order_by":1,"name":"Chang Tian","email":"","orcid":"","institution":"North China University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Chang","middleName":"","lastName":"Tian","suffix":""},{"id":333083202,"identity":"3e71a71f-c458-42cc-8857-b3f1fa28a96b","order_by":2,"name":"Jie Liu","email":"","orcid":"","institution":"North China University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Jie","middleName":"","lastName":"Liu","suffix":""},{"id":333083203,"identity":"238c316c-d522-4236-bc89-de8a03e4c703","order_by":3,"name":"Chong Di","email":"","orcid":"","institution":"Qilu University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Chong","middleName":"","lastName":"Di","suffix":""},{"id":333083205,"identity":"5e7631d9-6f73-4959-b015-5093072d8451","order_by":4,"name":"Keqing Ning","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxElEQVRIiWNgGAWjYDACZgYGxgYGGyiPjXgtaRAWcVoYwFoOk6DFnJ338MsZZefz+GfkH2D4UHaYgX92A34tls18aZYbzt0ulriRzMA449xhBok7B/BrMTjMY2b4sO124gaJZAZm3rbDDAYSCURpOQfR8pdILcYPN7YdgGhhJNYWoBeSE2eceWxwsOdcOo/EDUJazp8x/thTZpfY35748MGPMms5/hkEtAABmwQsOg4AMQ9B9UDA/IHoSB8Fo2AUjIKRCQCCLELkCI4yPgAAAABJRU5ErkJggg==","orcid":"","institution":"North China University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Keqing","middleName":"","lastName":"Ning","suffix":""}],"badges":[],"createdAt":"2024-07-19 10:37:36","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4767541/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4767541/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":62887585,"identity":"abf1723c-a830-4da7-8538-3f69418df744","added_by":"auto","created_at":"2024-08-20 16:21:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1069734,"visible":true,"origin":"","legend":"","description":"","filename":"ArticleTitle51.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4767541/v1_covered_489c45fc-5eeb-498f-8d85-757e65b1fca3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"HADT : Image Super-Resolution Restoration Using Hybrid Attention-Dense Connected Transformer Networks","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"world-wide-web","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"wwwj","sideBox":"Learn more about [World Wide Web](http://link.springer.com/journal/11280)","snPcode":"11280","submissionUrl":"https://submission.nature.com/new-submission/11280/3","title":"World Wide Web","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Hybrid attention transformer, Image super-resolution, Dense connection transformer","lastPublishedDoi":"10.21203/rs.3.rs-4767541/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4767541/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Image super-resolution (SR) plays a vital role in vision tasks, in which Transformer-based methods outperform conventional convolutional neural networks. Existing work usually uses residual linking to improve the performance, but this type of linking provides limited information transfer within the block. Also, in order to improve feature extraction, existing work usually restricts the self-attention computation to a single window. This means that transformer-based networks can only use feature information within a limited spatial range. To handle the challenge, this paper proposes a novel Hybrid Attention-Dense Connected Transformer Networks (HADT) to better utilise the potential feature information. HADT is constructed by stacking attentional transformer block (ATB), which contains Effective Dense Transformer Block (EDTB) and Hybrid Attention Block (HAB). EDTB combines dense connectivity and swin-transformer to enhance feature transfer and improve model representation, and meanwhile, HAB is used for cross-window information interaction and joint modelling of features for better visualisation. Based on the experiments, our method is effective on SR tasks with magnification factors of 2, 3, and 4. For example, using the Urban100 dataset in an experiment with an amplification factor of 4 our method has a PSNR value that is 0.15 dB higher than the previous method and reconstructs a more detailed texture.","manuscriptTitle":"HADT : Image Super-Resolution Restoration Using Hybrid Attention-Dense Connected Transformer Networks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-20 16:13:36","doi":"10.21203/rs.3.rs-4767541/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorAssigned","content":"","date":"2024-07-29T09:18:19+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-24T11:44:53+00:00","index":"","fulltext":""},{"type":"submitted","content":"World Wide Web","date":"2024-07-19T10:36:08+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"world-wide-web","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"wwwj","sideBox":"Learn more about [World Wide Web](http://link.springer.com/journal/11280)","snPcode":"11280","submissionUrl":"https://submission.nature.com/new-submission/11280/3","title":"World Wide Web","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"dace9bca-271a-46a9-b859-ca41e3580714","owner":[],"postedDate":"August 20th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2024-08-20T16:13:36+00:00","versionOfRecord":[],"versionCreatedAt":"2024-08-20 16:13:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4767541","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4767541","identity":"rs-4767541","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}