StyleMamba: Efficient Image Style Transfer with Bidirectional Selective Scan Vision Mamba

StyleMamba: Efficient Image Style Transfer with Bidirectional Selective Scan Vision Mamba | 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 StyleMamba: Efficient Image Style Transfer with Bidirectional Selective Scan Vision Mamba Jian Liu, Jun Yang, DiWei Wu, Hewen Liu, Jun Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8742918/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract Style transfer aims to render stylized images withartistic features while maintaining the original content.Traditional CNN-based approaches have limitations indealing with global information and long-range dependencies in style transfer. Existing transformer-basedapproaches, while mitigating these problems well, facehigh computational costs. Mamba addresses these limitations using a selective structured state-space model(S4), which maintains linear complexity while effectivelyhandling long-range dependencies. In this pa-per, wepropose StyleMamba, an efficient image style transfer architecture based on a Bidirectional Selective Scanmechanism, to address the challenge of balancing local and global dependencies with the computational efficiency of existing methods through spatial dyadic statespace modeling. In addition, we design Dynamic GateFusion (DGF) to fuse dual-path outputs based on feature relevance adaptively. Performing qualitative andquantitative experiments on representative datasets, wedemonstrate the advantages of our model over otherstate-of-the-art(SOTA) transformer-based methods anddifferent approaches. Image Style Transfer Bidirectional Selective Scan Mamba Enhance Efficiency Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 24 Feb, 2026 Editor assigned by journal 02 Feb, 2026 Submission checks completed at journal 02 Feb, 2026 First submitted to journal 30 Jan, 2026 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-8742918","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":596633743,"identity":"ef32d05a-d25c-427b-bd54-a63db0261a21","order_by":0,"name":"Jian Liu","email":"","orcid":"","institution":"SICHUAN NORMAL UNIVERSITY","correspondingAuthor":false,"prefix":"","firstName":"Jian","middleName":"","lastName":"Liu","suffix":""},{"id":596633744,"identity":"8a981b91-5c09-445b-927d-7a64832c7668","order_by":1,"name":"Jun Yang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7ElEQVRIiWNgGAWjYBACxh4wxcbAwN7AcAAilkCsFp4DRGph4IExJOAqCWhh7jljJsHYxpe4XfL5wwM/dxxm4GfPMWD4uQOPw3rb0oBa2BJ3zs4xONh75jCDZM8bA8beM3i09DMfA2vZcDuH4TBj22EGgxs5BsyMbfi0MLZBtNw8/gCsxZ6glt5mqC03GAwgtkgQ0tJzLNmC4Ryb8YYzIL+0pfNInHlWAGTg1mLYk2N4g6HsmOyG48cff/jZZi3H35688cFPfFoaGFik/7IdgwuA4+kAbg0MDPLAqPnA8KcGn5pRMApGwSgY6QAAGIdT2jXPodoAAAAASUVORK5CYII=","orcid":"","institution":"SICHUAN NORMAL UNIVERSITY","correspondingAuthor":true,"prefix":"","firstName":"Jun","middleName":"","lastName":"Yang","suffix":""},{"id":596633745,"identity":"c375f3c5-7032-4322-a268-5c3fffeb4acb","order_by":2,"name":"DiWei Wu","email":"","orcid":"","institution":"SICHUAN NORMAL UNIVERSITY","correspondingAuthor":false,"prefix":"","firstName":"DiWei","middleName":"","lastName":"Wu","suffix":""},{"id":596633746,"identity":"c19cd3d4-87a0-4bdc-8302-5bb72b174a36","order_by":3,"name":"Hewen Liu","email":"","orcid":"","institution":"SICHUAN NORMAL UNIVERSITY","correspondingAuthor":false,"prefix":"","firstName":"Hewen","middleName":"","lastName":"Liu","suffix":""},{"id":596633747,"identity":"b2be0bff-b78c-458f-915a-f59fba6047fe","order_by":4,"name":"Jun Liu","email":"","orcid":"","institution":"SICHUAN NORMAL UNIVERSITY","correspondingAuthor":false,"prefix":"","firstName":"Jun","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2026-01-30 15:53:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8742918/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8742918/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104398200,"identity":"f8416b2d-34af-4044-9d82-2c2741c98b3d","added_by":"auto","created_at":"2026-03-11 12:00:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4146776,"visible":true,"origin":"","legend":"","description":"","filename":"ArticleTitle1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8742918/v1_covered_a6324003-396a-4f01-8894-3559020abb89.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"StyleMamba: Efficient Image Style Transfer with Bidirectional Selective Scan Vision Mamba","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":"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":"Image Style Transfer, Bidirectional Selective Scan Mamba, Enhance Efficiency","lastPublishedDoi":"10.21203/rs.3.rs-8742918/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8742918/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eStyle transfer aims to render stylized images withartistic features while maintaining the original content.Traditional CNN-based approaches have limitations indealing with global information and long-range dependencies in style transfer. Existing transformer-basedapproaches, while mitigating these problems well, facehigh computational costs. Mamba addresses these limitations using a selective structured state-space model(S4), which maintains linear complexity while effectivelyhandling long-range dependencies. In this pa-per, wepropose StyleMamba, an efficient image style transfer architecture based on a Bidirectional Selective Scanmechanism, to address the challenge of balancing local and global dependencies with the computational efficiency of existing methods through spatial dyadic statespace modeling. In addition, we design Dynamic GateFusion (DGF) to fuse dual-path outputs based on feature relevance adaptively. Performing qualitative andquantitative experiments on representative datasets, wedemonstrate the advantages of our model over otherstate-of-the-art(SOTA) transformer-based methods anddifferent approaches.\u003c/p\u003e","manuscriptTitle":"StyleMamba: Efficient Image Style Transfer with Bidirectional Selective Scan Vision Mamba","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-27 04:46:36","doi":"10.21203/rs.3.rs-8742918/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2026-02-25T03:26:54+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-02T11:43:12+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-02T11:39:23+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2026-01-30T15:50:38+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":"479ab779-90d5-463e-951d-8712863e176e","owner":[],"postedDate":"February 27th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-02-27T04:46:36+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-27 04:46:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8742918","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8742918","identity":"rs-8742918","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}