Research on multimodal conditional diffusion image translation technology based on dynamic door control and attention masking

Research on multimodal conditional diffusion image translation technology based on dynamic door control and attention masking | 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 Research on multimodal conditional diffusion image translation technology based on dynamic door control and attention masking xiaoli zhang, mengxiang liu, yusi wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8587856/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract In image translation from virtual to real-world autonomous driving scenarios, the conditional diffusion model for multimodal data fusion employs a multi-head self-attention mechanism to model cross-modal global dependencies between semantic segmentation maps and depth maps for scene generation. However, it still has limitations: the translated results exhibit discrepancies in the consistency between semantic contours and spatial depth, failing to meet high-precision requirements; multimodal data quality is uneven, and using a fixed-weight fusion method is susceptible to the influence of low-quality modalities; background noise and modal noise weaken the constraining effect of key features on the denoising process. To address these issues, this paper proposes an improved multi-modal feature fusion framework. The multi-head self-attention mechanism incorporates a dynamic gating module, enabling cross-modal feature weights to be adaptively modulated through spatial semantic importance assessment and channel-modal contribution quantification, thereby balancing the proportions of high- and low-quality modalities. An attention masking mechanism is introduced, using learnable masks to filter out interference from non-critical regions, thereby enhancing the representation of core elements such as vehicles and traffic signs. The optimized multimodal features are incorporated into the denoising process of the diffusion model as dual conditions, guiding the noise prediction network to align semantic and depth constraints at the pixel level, thereby achieving precise translation from virtual to real scenes. Experimental results show that the improved model achieves significantly enhanced translation accuracy on the Cityscapes dataset, with superior performance on metrics such as Fréchet Inception Distance (FID) and Learned Perceptual Image Patch Similarity (LPIPS), achieving values of 42.80 and 0.412, respectively. Physical sciences/Engineering Physical sciences/Mathematics and computing Dynamic gate mechanism Image translation Diffusion model Multimodal fusion Virtual to reality Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 06 Apr, 2026 Reviewers agreed at journal 17 Mar, 2026 Reviewers invited by journal 04 Feb, 2026 Editor assigned by journal 30 Jan, 2026 Editor invited by journal 30 Jan, 2026 Submission checks completed at journal 28 Jan, 2026 First submitted to journal 28 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-8587856","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":586068429,"identity":"7d6d85da-4662-49af-a743-a7adaa45979b","order_by":0,"name":"xiaoli zhang","email":"","orcid":"","institution":"Changsha Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"xiaoli","middleName":"","lastName":"zhang","suffix":""},{"id":586068430,"identity":"2d7405ea-aa65-45ea-91ef-2a97809c5e8c","order_by":1,"name":"mengxiang liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5ElEQVRIie3RsYrCMBzH8ZRAbknPNYLoK/xLobcc+CopB9dJcHSsCOkr9CVuEopjIKBLwLXDDbp0rrOD/js6GDM65DsEAvnwG0JIKPSGjSjVIOF7Ski01lFJ+EsyrpRc9qvfFEnpR8BauNTW5CVeBuJRK5NtrGjxVxlc2f1PQNPu5BJRLX/SWLFFY3MktuOg2Re4CBVyj4QvGj0QZZBwJlyEiby6xkoU2fHsSTg3JKktyKz1XREfikC/kknT4kqOZGxY5iRzM+rxK2+z7FicTxdl5p+HTeckj8nhoP7vQ6FQKPSkO6I9UrRdWK75AAAAAElFTkSuQmCC","orcid":"","institution":"Changsha Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"mengxiang","middleName":"","lastName":"liu","suffix":""},{"id":586068431,"identity":"32341b06-91c4-4d26-9ad8-c32208b2a966","order_by":2,"name":"yusi wang","email":"","orcid":"","institution":"Changsha Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"yusi","middleName":"","lastName":"wang","suffix":""}],"badges":[],"createdAt":"2026-01-13 06:09:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8587856/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8587856/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102296764,"identity":"0c1384b2-dbc1-4293-b556-87e79542f75a","added_by":"auto","created_at":"2026-02-10 10:21:28","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":717043,"visible":true,"origin":"","legend":"","description":"","filename":"multimodalconditionaldiffusionimagetranslation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8587856/v1_covered_569eab56-a135-495b-a7d1-f6756865f7b9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Research on multimodal conditional diffusion image translation technology based on dynamic door control and attention masking","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":"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":"Dynamic gate mechanism, Image translation, Diffusion model, Multimodal fusion, Virtual to reality","lastPublishedDoi":"10.21203/rs.3.rs-8587856/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8587856/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn image translation from virtual to real-world autonomous driving scenarios, the conditional diffusion model for multimodal data fusion employs a multi-head self-attention mechanism to model cross-modal global dependencies between semantic segmentation maps and depth maps for scene generation. However, it still has limitations: the translated results exhibit discrepancies in the consistency between semantic contours and spatial depth, failing to meet high-precision requirements; multimodal data quality is uneven, and using a fixed-weight fusion method is susceptible to the influence of low-quality modalities; background noise and modal noise weaken the constraining effect of key features on the denoising process. To address these issues, this paper proposes an improved multi-modal feature fusion framework. The multi-head self-attention mechanism incorporates a dynamic gating module, enabling cross-modal feature weights to be adaptively modulated through spatial semantic importance assessment and channel-modal contribution quantification, thereby balancing the proportions of high- and low-quality modalities. An attention masking mechanism is introduced, using learnable masks to filter out interference from non-critical regions, thereby enhancing the representation of core elements such as vehicles and traffic signs. The optimized multimodal features are incorporated into the denoising process of the diffusion model as dual conditions, guiding the noise prediction network to align semantic and depth constraints at the pixel level, thereby achieving precise translation from virtual to real scenes. Experimental results show that the improved model achieves significantly enhanced translation accuracy on the Cityscapes dataset, with superior performance on metrics such as Fr\u0026eacute;chet Inception Distance (FID) and Learned Perceptual Image Patch Similarity (LPIPS), achieving values of 42.80 and 0.412, respectively.\u003c/p\u003e","manuscriptTitle":"Research on multimodal conditional diffusion image translation technology based on dynamic door control and attention masking","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-09 02:51:27","doi":"10.21203/rs.3.rs-8587856/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-04-06T14:48:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"316827486292671123188832844044533135572","date":"2026-03-17T09:16:55+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-05T04:11:24+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-30T21:59:14+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-01-30T21:53:04+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-28T10:16:46+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-01-28T08:29:46+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":"d9e67ea3-bb48-43da-b6b4-fb1f940c77f2","owner":[],"postedDate":"February 9th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":62352919,"name":"Physical sciences/Engineering"},{"id":62352920,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-02-09T02:51:28+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-09 02:51:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8587856","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8587856","identity":"rs-8587856","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}