Ro-FusionGAN:An Adversarial Framework for High-Quality Multi-focus image fusion

Ro-FusionGAN:An Adversarial Framework for High-Quality Multi-focus image fusion | 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 Ro-FusionGAN:An Adversarial Framework for High-Quality Multi-focus image fusion Yongli Xian, Heng Zhou, Zhijie Gong, Congzheng Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9113517/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 Multi-focus image fusion (MFIF) aims to synthesize an all-in-focus image from source images with varying focal depths. While deep learning has advanced this field, existing "process-imitation" approaches often rely on binary mask supervision, leading to boundary artifacts and a dependency on heuristic post-processing. To address these limitations, we propose Result-Oriented Fusion Generative Adversarial Network (Ro-FusionGAN), a novel result-oriented adversarial framework. Unlike methods that mimic intermediate focus maps, our framework directly optimizes the perceptual quality of the final fused image via a composite fusion-aware loss function. Furthermore, we introduce a differentiable Total Variation (TV) regularizer to autonomously enforce spatial smoothness, enabling the generation of soft decision maps and eliminating the need for post-processing. Extensive experiments demonstrate that Ro-FusionGAN outperforms eleven state-of-the-art methods in visual quality, quantitative metrics, and computational efficiency, yielding artifact-free images with natural focus transitions. Multi-focus image fusion Generative Adversarial Network Result-Oriented Learning Soft Decision Map End-to-End. Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 02 Apr, 2026 Reviews received at journal 02 Apr, 2026 Reviewers agreed at journal 22 Mar, 2026 Reviewers invited by journal 17 Mar, 2026 Editor assigned by journal 16 Mar, 2026 Submission checks completed at journal 16 Mar, 2026 First submitted to journal 13 Mar, 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-9113517","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":607471743,"identity":"3768b49e-2ac9-4ff8-b1bd-e84cf4d048ed","order_by":0,"name":"Yongli Xian","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/UlEQVRIiWNgGAWjYFAC5oYDH37YAGnmBpiQAQEtjI0HZ/akAbUwNsBUE9TSfJiH7TCIQaQWgxuJDQd4eM5H87czNjDz/Pkjz8DevE2CoeYOTi2SM4BaJCxu5844DNTC22Zg2MBzrEyC4dgznFr4JYBaDHhu5zaAtTQYJDBI5JhJMDYcxqmFDaQlge1c7vzDYIcBtci/wa8FbMsBtgO5G8Ba2EC28ODXItnzsOFgY09y7kagloNz24wN23jSii0SjuHWYnA8+fDnPz/scuedP3zwwZs/cvL87Ic33vhQg1sLg0ACgn0A7DsQkYBFJcIzB/DJjoJRMApGwSgAAgDF5FfBqfu+JAAAAABJRU5ErkJggg==","orcid":"","institution":"Xihua University","correspondingAuthor":true,"prefix":"","firstName":"Yongli","middleName":"","lastName":"Xian","suffix":""},{"id":607471744,"identity":"4291f54d-2ee7-4de7-b70c-19359b8b1046","order_by":1,"name":"Heng Zhou","email":"","orcid":"","institution":"Xihua University","correspondingAuthor":false,"prefix":"","firstName":"Heng","middleName":"","lastName":"Zhou","suffix":""},{"id":607471748,"identity":"f29b1a04-0e66-4222-a8fe-95fb1ff5185d","order_by":2,"name":"Zhijie Gong","email":"","orcid":"","institution":"Xihua University","correspondingAuthor":false,"prefix":"","firstName":"Zhijie","middleName":"","lastName":"Gong","suffix":""},{"id":607471749,"identity":"1e669e20-63b2-4c87-8b09-d1da7a212a37","order_by":3,"name":"Congzheng Wang","email":"","orcid":"","institution":"Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Congzheng","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2026-03-13 10:23:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9113517/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9113517/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105035746,"identity":"25d669a3-a38f-48cb-bd33-dc9dd5a84ae3","added_by":"auto","created_at":"2026-03-20 07:26:33","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":8091561,"visible":true,"origin":"","legend":"","description":"","filename":"RoFusion.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9113517/v1_covered_88e7ead3-c0f2-4294-a10d-148c1197f3b4.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Ro-FusionGAN:An Adversarial Framework for\nHigh-Quality Multi-focus image fusion","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":"Multi-focus image fusion, Generative Adversarial Network, Result-Oriented Learning, Soft Decision Map, End-to-End.","lastPublishedDoi":"10.21203/rs.3.rs-9113517/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9113517/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMulti-focus image fusion (MFIF) aims to synthesize an all-in-focus image from source images with varying focal depths. While deep learning has advanced this field, existing \"process-imitation\" approaches often rely on binary mask supervision, leading to boundary artifacts and a dependency on heuristic post-processing. To address these limitations, we propose Result-Oriented Fusion Generative Adversarial Network (Ro-FusionGAN), a novel result-oriented adversarial framework. Unlike methods that mimic intermediate focus maps, our framework directly optimizes the perceptual quality of the final fused image via a composite fusion-aware loss function. Furthermore, we introduce a differentiable Total Variation (TV) regularizer to autonomously enforce spatial smoothness, enabling the generation of soft decision maps and eliminating the need for post-processing. Extensive experiments demonstrate that Ro-FusionGAN outperforms eleven state-of-the-art methods in visual quality, quantitative metrics, and computational efficiency, yielding artifact-free images with natural focus transitions.\u003c/p\u003e","manuscriptTitle":"Ro-FusionGAN:An Adversarial Framework for\nHigh-Quality Multi-focus image fusion","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-19 16:50:28","doi":"10.21203/rs.3.rs-9113517/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-02T23:40:24+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-02T14:28:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"231053678489601490062684711877057935263","date":"2026-03-23T01:11:17+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-17T05:37:35+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-16T09:27:17+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-16T09:26:37+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2026-03-13T10:06:54+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":"924e7e61-599a-4ab2-ad2a-c9099b42998f","owner":[],"postedDate":"March 19th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-21T15:38:15+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-19 16:50:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9113517","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9113517","identity":"rs-9113517","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}