CAF-VTON: Cross-Attention Layered Fusion Based Latent Diffusion Virtual Try-On

CAF-VTON: Cross-Attention Layered Fusion Based Latent Diffusion Virtual Try-On | 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 CAF-VTON: Cross-Attention Layered Fusion Based Latent Diffusion Virtual Try-On Xiangyan Fu, Mingquan Zhou, Weihua Pu, Shengling Geng, Lin Gan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6304101/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 05 Sep, 2025 Read the published version in Signal, Image and Video Processing → Version 1 posted 6 You are reading this latest preprint version Abstract Virtual try-on technology has gained significant attention in e-commerce, digital retail, and virtual reality due to its ability to enhance user experience and reduce return rates. However, generating accurate and natural virtual try-on results remains challenging, especially when dealing with complex human poses and clothing deformations. In this paper, we propose CAF-VTON, a novel latent diffusion-based virtual try-on network that introduces cross-attention layered fusion for the first time in virtual try-on tasks. By leveraging a layered cross-attention mechanism, CAF-VTON can progressively extract both local and global features of human poses and clothing, enabling the capture of fine details essential for realistic virtual try-on. Here we show that CAF-VTON outperforms existing methods on high-resolution datasets, achieving state-of-the-art performance in terms of realism, detail fidelity, and pose consistency. Our work paves the way for more advanced virtual try-on solutions, offering broader applications in the fashion and retail industries. Virtual Try-On Latent Diffusion Layered Fusion Cross-Attention Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 05 Sep, 2025 Read the published version in Signal, Image and Video Processing → Version 1 posted Editorial decision: Revision requested 17 Apr, 2025 Reviews received at journal 15 Apr, 2025 Reviewers agreed at journal 13 Apr, 2025 Reviewers invited by journal 12 Apr, 2025 Submission checks completed at journal 07 Apr, 2025 First submitted to journal 06 Apr, 2025 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-6304101","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":444622126,"identity":"dcb3e663-d085-4765-b980-6f426170205c","order_by":0,"name":"Xiangyan Fu","email":"","orcid":"","institution":"Qinghai Normal University","correspondingAuthor":false,"prefix":"","firstName":"Xiangyan","middleName":"","lastName":"Fu","suffix":""},{"id":444622128,"identity":"e880ed7a-ed0b-4220-a7de-d8699aaadeb7","order_by":1,"name":"Mingquan Zhou","email":"data:image/png;base64,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","orcid":"","institution":"Qinghai Normal University","correspondingAuthor":true,"prefix":"","firstName":"Mingquan","middleName":"","lastName":"Zhou","suffix":""},{"id":444622130,"identity":"0f4a822e-9f65-4980-a4ff-d6c46b225606","order_by":2,"name":"Weihua Pu","email":"","orcid":"","institution":"Shaanxi Fashion Engineering University","correspondingAuthor":false,"prefix":"","firstName":"Weihua","middleName":"","lastName":"Pu","suffix":""},{"id":444622134,"identity":"0aa181ff-255b-40d0-834b-9c9553ee76c3","order_by":3,"name":"Shengling Geng","email":"","orcid":"","institution":"Qinghai Normal University","correspondingAuthor":false,"prefix":"","firstName":"Shengling","middleName":"","lastName":"Geng","suffix":""},{"id":444622135,"identity":"ef30b7d0-f8d0-40fc-8ab4-604ddd0b5562","order_by":4,"name":"Lin Gan","email":"","orcid":"","institution":"Shaanxi Fashion Engineering University","correspondingAuthor":false,"prefix":"","firstName":"Lin","middleName":"","lastName":"Gan","suffix":""}],"badges":[],"createdAt":"2025-03-25 13:09:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6304101/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6304101/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11760-025-04388-x","type":"published","date":"2025-09-05T15:58:02+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":90827979,"identity":"826e387a-c34d-44d9-ae81-f880c3f798d2","added_by":"auto","created_at":"2025-09-08 16:04:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2290606,"visible":true,"origin":"","legend":"","description":"","filename":"CAFVTON.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6304101/v1_covered_0d7a1d32-4746-44b6-a4ea-12c09e1bc737.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eCAF-VTON: Cross-Attention Layered Fusion Based Latent Diffusion Virtual Try-On\u003c/p\u003e","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":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Virtual Try-On, Latent Diffusion, Layered Fusion Cross-Attention","lastPublishedDoi":"10.21203/rs.3.rs-6304101/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6304101/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Virtual try-on technology has gained significant attention in e-commerce, digital retail, and virtual reality due to its ability to enhance user experience and reduce return rates. However, generating accurate and natural virtual try-on results remains challenging, especially when dealing with complex human poses and clothing deformations. In this paper, we propose CAF-VTON, a novel latent diffusion-based virtual try-on network that introduces cross-attention layered fusion for the first time in virtual try-on tasks. By leveraging a layered cross-attention mechanism, CAF-VTON can progressively extract both local and global features of human poses and clothing, enabling the capture of fine details essential for realistic virtual try-on. Here we show that CAF-VTON outperforms existing methods on high-resolution datasets, achieving state-of-the-art performance in terms of realism, detail fidelity, and pose consistency. Our work paves the way for more advanced virtual try-on solutions, offering broader applications in the fashion and retail industries.","manuscriptTitle":"CAF-VTON: Cross-Attention Layered Fusion Based Latent Diffusion Virtual Try-On","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-21 15:37:29","doi":"10.21203/rs.3.rs-6304101/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-04-18T01:19:34+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-15T11:55:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"57301664296021459834124225118103444931","date":"2025-04-13T11:28:04+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-13T03:44:53+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-07T06:53:32+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2025-04-06T12:27:42+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"093d026d-417f-4e18-bac7-7dc4a5b4f3eb","owner":[],"postedDate":"April 21st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-09-08T16:01:42+00:00","versionOfRecord":{"articleIdentity":"rs-6304101","link":"https://doi.org/10.1007/s11760-025-04388-x","journal":{"identity":"signal-image-and-video-processing","isVorOnly":false,"title":"Signal, Image and Video Processing"},"publishedOn":"2025-09-05 15:58:02","publishedOnDateReadable":"September 5th, 2025"},"versionCreatedAt":"2025-04-21 15:37:29","video":"","vorDoi":"10.1007/s11760-025-04388-x","vorDoiUrl":"https://doi.org/10.1007/s11760-025-04388-x","workflowStages":[]},"version":"v1","identity":"rs-6304101","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6304101","identity":"rs-6304101","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}