UNet-like network fused Swin Transformer and CNN for Semantic Image Synthesis

UNet-like network fused Swin Transformer and CNN for Semantic Image Synthesis | 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 UNet-like network fused Swin Transformer and CNN for Semantic Image Synthesis Aihua Ke, Jian Luo, Bo Cai This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4023692/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 20 Jul, 2024 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract Semantic image synthesis approaches has been dominated by the modelling of Convolutional Neural Networks (CNN). Due to the limitations of local perception, their performance improvement seems to have plateaued in recent years. To tackle this issue, we propose the TransUNet model, which is a UNet-like network fused Swin Transformer and CNN for semantic image synthesis. Photorealistic image synthesis conditional on the given semantic layout depends on the high-level semantics and the low-level positions. To improve the synthesis performance, we design a novel conditional residual fusion module for the model decoder to efficiently fuse the hierarchical feature maps extracted at different scales. Moreover, this module combines the opposition-based learning mechanism and the weight assignment mechanism for enhancing and attending the semantic information. Compared to pure CNN-based models, our TransUNet combines the local and global perceptions to better extract high- and low-level features and better fuse multi-scale features. We have conducted an extensive amount of comparison experiments, both in quantitative and qualitative terms, to validate the effectiveness of our proposed TransUNet model for semantic image synthesis. The outcomes illustrate that TransUNet distinctively outperforms the state-of-the-art model on three benchmark datasets (Citysacpes, ADE20K, and COCO-Stuff) including numerous real-scene images. Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 20 Jul, 2024 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 08 May, 2024 Reviews received at journal 06 May, 2024 Reviewers agreed at journal 01 May, 2024 Reviews received at journal 12 Apr, 2024 Reviewers agreed at journal 02 Apr, 2024 Reviewers invited by journal 02 Apr, 2024 Editor assigned by journal 02 Apr, 2024 Editor invited by journal 28 Mar, 2024 Submission checks completed at journal 28 Mar, 2024 First submitted to journal 07 Mar, 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-4023692","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":285771298,"identity":"ceacaced-6135-4090-93e3-8aa51091f826","order_by":0,"name":"Aihua Ke","email":"","orcid":"","institution":"Wuhan University","correspondingAuthor":false,"prefix":"","firstName":"Aihua","middleName":"","lastName":"Ke","suffix":""},{"id":285771299,"identity":"2a13e708-f5a4-4e47-812e-5b702c1f9eb0","order_by":1,"name":"Jian Luo","email":"","orcid":"","institution":"Wuhan University","correspondingAuthor":false,"prefix":"","firstName":"Jian","middleName":"","lastName":"Luo","suffix":""},{"id":285771300,"identity":"840f9cd7-f978-46bc-bf09-fc793d1ce5ae","order_by":2,"name":"Bo Cai","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAArklEQVRIiWNgGAWjYFACxjaGDwwHQCwD4rUwziBRCwMbMw9JWvjbD7c9tm27k9jA3rxNgqHmDmEtEmcS241z254lNvAcK5NgOPaMsBYDhsQ26dxthxMbJHLMJBgbDhOhhf9hm7QlSIv8G2K1SABtYQTbwkOkFokbD9sNe/8dNm7jSSu2SDhGhBb+/vRnD36cOSzbz354440PNURogQM2EJFAgoZRMApGwSgYBXgAACC1OwtdyztBAAAAAElFTkSuQmCC","orcid":"","institution":"Wuhan University","correspondingAuthor":true,"prefix":"","firstName":"Bo","middleName":"","lastName":"Cai","suffix":""}],"badges":[],"createdAt":"2024-03-07 09:00:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4023692/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4023692/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-024-65585-1","type":"published","date":"2024-07-21T03:48:49+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":60756872,"identity":"9b8cd54e-5667-4150-80c7-723af779640a","added_by":"auto","created_at":"2024-07-21 03:48:58","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1313036,"visible":true,"origin":"","legend":"","description":"","filename":"UNetlikenetworkfusedSwinTransformerandCNNforSemanticImageSynthesis040320.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4023692/v1_covered_25ad7909-d8c4-4985-82ee-7b2d46dcfc7f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"UNet-like network fused Swin Transformer and CNN for Semantic Image Synthesis","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":"","lastPublishedDoi":"10.21203/rs.3.rs-4023692/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4023692/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Semantic image synthesis approaches has been dominated by the modelling of Convolutional Neural Networks (CNN). Due to the limitations of local perception, their performance improvement seems to have plateaued in recent years. To tackle this issue, we propose the TransUNet model, which is a UNet-like network fused Swin Transformer and CNN for semantic image synthesis. Photorealistic image synthesis conditional on the given semantic layout depends on the high-level semantics and the low-level positions. To improve the synthesis performance, we design a novel conditional residual fusion module for the model decoder to efficiently fuse the hierarchical feature maps extracted at different scales. Moreover, this module combines the opposition-based learning mechanism and the weight assignment mechanism for enhancing and attending the semantic information. Compared to pure CNN-based models, our TransUNet combines the local and global perceptions to better extract high- and low-level features and better fuse multi-scale features. We have conducted an extensive amount of comparison experiments, both in quantitative and qualitative terms, to validate the effectiveness of our proposed TransUNet model for semantic image synthesis. The outcomes illustrate that TransUNet distinctively outperforms the state-of-the-art model on three benchmark datasets (Citysacpes, ADE20K, and COCO-Stuff) including numerous real-scene images.","manuscriptTitle":"UNet-like network fused Swin Transformer and CNN for Semantic Image Synthesis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-01 17:54:47","doi":"10.21203/rs.3.rs-4023692/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-05-08T08:38:22+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-05-06T20:18:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"afe664f9-86c3-4065-ba3a-0fefe50172d7","date":"2024-05-01T13:50:10+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-04-12T07:12:15+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"21586b8b-0a07-48e3-a3ae-155bc2f80603_SNPRID","date":"2024-04-02T14:37:12+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-04-02T14:01:00+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-04-02T06:32:17+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-03-28T05:07:31+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-03-28T04:54:57+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-03-07T08:51:23+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":"5ffe1443-3838-42f8-b1b5-2e1db6e7d268","owner":[],"postedDate":"April 1st, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-07-21T03:48:49+00:00","versionOfRecord":{"articleIdentity":"rs-4023692","link":"https://doi.org/10.1038/s41598-024-65585-1","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2024-07-21 03:48:49","publishedOnDateReadable":"July 21st, 2024"},"versionCreatedAt":"2024-04-01 17:54:47","video":"","vorDoi":"10.1038/s41598-024-65585-1","vorDoiUrl":"https://doi.org/10.1038/s41598-024-65585-1","workflowStages":[]},"version":"v1","identity":"rs-4023692","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4023692","identity":"rs-4023692","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}