StackMFF: End-to-end Multi-Focus Image Stack Fusion Network

StackMFF: End-to-end Multi-Focus Image Stack Fusion Network | 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 StackMFF: End-to-end Multi-Focus Image Stack Fusion Network Xinzhe Xie, Qingyan Jiang, Dong Chen, Buyu Guo, Peiliang Li, Sangjun Zhou This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5315538/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Existing end-to-end multi-focus image fusion networks demonstrate efficacy in merging two images but often introduce various types of image degradation due to error accumulation resulting from iterative fusion when applied to image stacks. To address this limitation, we propose a novel approach that directly fuses the entire image stack using a specially designed 3D convolutional neural network. The proposed method leverages an innovative training pipeline based on monocular depth estimation to generate a large-scale dataset, ensuring robust performance across diverse scenarios. Furthermore, to facilitate comprehensive evaluation and comparison within the field, we establish a benchmark for this field and release a comprehensive toolbox encompassing 12 distinct algorithms. Extensive experimental results demonstrate that our proposed method effectively fuses multi-focus image stacks while mitigating image degradation, achieving state-of-the-art performance in both fusion quality and processing speed. The codes are available at https://github.com/Xinzhe99/StackMFF. Artificial Intelligence and Machine Learning Deep learning multi-focus image stack fusion 3D CNNs synthetic dataset Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted 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-5315538","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":369326628,"identity":"570c4023-bc71-4b03-be95-25a29a7b1f2a","order_by":0,"name":"Xinzhe Xie","email":"","orcid":"https://orcid.org/0009-0008-6081-5654","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Xinzhe","middleName":"","lastName":"Xie","suffix":""},{"id":369326629,"identity":"72ee29e1-c2e5-4e69-8451-1d6af21f3216","order_by":1,"name":"Qingyan Jiang","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Qingyan","middleName":"","lastName":"Jiang","suffix":""},{"id":369326630,"identity":"1eba599b-f0c7-45fb-98e0-0bc42711a143","order_by":2,"name":"Dong Chen","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Dong","middleName":"","lastName":"Chen","suffix":""},{"id":369326631,"identity":"88753f81-5a1e-41ae-ae7f-514b129f216e","order_by":3,"name":"Buyu Guo","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxklEQVRIiWNgGAWjYHACNhjN+CChooY0LcwGD84cI00Lm+TDFmbC6uUjko895m07nNgvfSytIrGBjYG/vTsBrxbDG2npxiAtM/vSjt1I3CHDIHHm7Ab8WmbkmEkDteRuOMPediPxDBuDgUQuCVoKEtuYCWuRl4BrYTvGQJQWA55n6YZzzqXXz+xhS5ZIOHOMh6Bf5NuTjz14U2ZtzM/DZvjxR0WNHH97LwFbDgAJRjaEAA9e5WBbGkDkH4LqRsEoGAWjYCQDAOMFSGTQVPD3AAAAAElFTkSuQmCC","orcid":"","institution":"Donghai Laboratory","correspondingAuthor":true,"prefix":"","firstName":"Buyu","middleName":"","lastName":"Guo","suffix":""},{"id":369326632,"identity":"1be14b39-ad84-49df-99a3-a8a24f0fcdd4","order_by":4,"name":"Peiliang Li","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Peiliang","middleName":"","lastName":"Li","suffix":""},{"id":369326633,"identity":"87468a83-d591-49fc-87af-59db5329f2e2","order_by":5,"name":"Sangjun Zhou","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Sangjun","middleName":"","lastName":"Zhou","suffix":""}],"badges":[],"createdAt":"2024-10-23 04:23:52","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-5315538/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5315538/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":67345734,"identity":"90a8eeb7-0964-46ed-8e93-d8006aee2cae","added_by":"auto","created_at":"2024-10-24 02:23:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3922827,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerStackMFFpre1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5315538/v1_covered_64e932a1-b955-4ddc-ab95-d5602e59835e.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eStackMFF: End-to-end Multi-Focus Image Stack Fusion Network\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Hainan Institute of Zhejiang University","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Deep learning, multi-focus image stack fusion, 3D CNNs, synthetic dataset","lastPublishedDoi":"10.21203/rs.3.rs-5315538/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5315538/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eExisting end-to-end multi-focus image fusion networks demonstrate efficacy in merging two images but often introduce various types of image degradation due to error accumulation resulting from iterative fusion when applied to image stacks. To address this limitation, we propose a novel approach that directly fuses the entire image stack using a specially designed 3D convolutional neural network. The proposed method leverages an innovative training pipeline based on monocular depth estimation to generate a large-scale dataset, ensuring robust performance across diverse scenarios. Furthermore, to facilitate comprehensive evaluation and comparison within the field, we establish a benchmark for this field and release a comprehensive toolbox encompassing 12 distinct algorithms. Extensive experimental results demonstrate that our proposed method effectively fuses multi-focus image stacks while mitigating image degradation, achieving state-of-the-art performance in both fusion quality and processing speed. The codes are available at https://github.com/Xinzhe99/StackMFF.\u003c/p\u003e","manuscriptTitle":"StackMFF: End-to-end Multi-Focus Image Stack Fusion Network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-10-24 02:15:37","doi":"10.21203/rs.3.rs-5315538/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"849c812c-95e7-4685-a252-c7eb1de236e5","owner":[],"postedDate":"October 24th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":39301776,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2024-10-24T02:15:37+00:00","versionOfRecord":[],"versionCreatedAt":"2024-10-24 02:15:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5315538","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5315538","identity":"rs-5315538","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}