MSU-Mamba: Multi-Scale Defocus Blur Detection Using Cross-Scale Fusion and State Space Models

MSU-Mamba: Multi-Scale Defocus Blur Detection Using Cross-Scale Fusion and State Space Models | 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 MSU-Mamba: Multi-Scale Defocus Blur Detection Using Cross-Scale Fusion and State Space Models Xijun Wang, Xin Zhou, Yi Wang, Songto Zeng, Xinyu Liu, Haobo Shen, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5719588/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 11 Mar, 2025 Read the published version in The Visual Computer → Version 1 posted 9 You are reading this latest preprint version Abstract Defocus blur detection (DBD) plays a pivotal role in computer vision, serving as a fundamental step to enhance the performance of various downstream applications, such as image refocusing, depth estimation, and saliency detection. Despite recent advancements, existing methods often struggle in complex scenes with homogeneous regions, subtle blur transitions, and cluttered backgrounds. In this paper, we develop a novel approach (MSU-Mamba) to combine a multi-scale feature extraction with state-space modeling for boosting defocus blur detection. To do so, we develop a Multi-Scale Fusion (MSF) Block to integrate long-range dependency features across multiple scales to enhance feature representation. Moreover, in our MSF block, we devise a cross-scale token scanning mechanism into the original Mamba to better distinguish blurred and sharp regions. Comprehensive experiments conducted on benchmark datasets show that our MSU-Mamba outperforms state-of-the-art methods in terms of F-measure and MAE. The results validate our approach as a promising solution to the challenges of defocus blur detection and its application to downstream tasks. Defocus Blur Detection Multi-Scale Fusion State Space Model Cross-Scale Scanning Image Segmentation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 11 Mar, 2025 Read the published version in The Visual Computer → Version 1 posted Editorial decision: Revision requested 17 Jan, 2025 Reviews received at journal 14 Jan, 2025 Reviews received at journal 12 Jan, 2025 Reviewers agreed at journal 07 Jan, 2025 Reviewers agreed at journal 05 Jan, 2025 Reviewers invited by journal 04 Jan, 2025 Editor assigned by journal 27 Dec, 2024 Submission checks completed at journal 27 Dec, 2024 First submitted to journal 27 Dec, 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-5719588","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":395105274,"identity":"4e68ab6f-4e08-44ef-af70-7e9bcbb07cad","order_by":0,"name":"Xijun Wang","email":"","orcid":"","institution":"Guangzhou Power Supply Bureau Co., Ltd, China.","correspondingAuthor":false,"prefix":"","firstName":"Xijun","middleName":"","lastName":"Wang","suffix":""},{"id":395105275,"identity":"6423f6cd-6db7-453e-bee2-9b571bc625c5","order_by":1,"name":"Xin Zhou","email":"","orcid":"","institution":"Guangzhou Power Supply Bureau Co., Ltd, China.","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Zhou","suffix":""},{"id":395105276,"identity":"d6f06787-0c8d-4955-a017-d4754976ce77","order_by":2,"name":"Yi Wang","email":"","orcid":"","institution":"Guangzhou Power Supply Bureau Co., Ltd, China.","correspondingAuthor":false,"prefix":"","firstName":"Yi","middleName":"","lastName":"Wang","suffix":""},{"id":395105277,"identity":"6b2197d8-d81c-49ba-a0e5-468b076aa151","order_by":3,"name":"Songto Zeng","email":"","orcid":"","institution":"Guangzhou Power Supply Bureau Co., Ltd, China.","correspondingAuthor":false,"prefix":"","firstName":"Songto","middleName":"","lastName":"Zeng","suffix":""},{"id":395105278,"identity":"ea476788-a92f-41a9-a593-5ec08398e8d3","order_by":4,"name":"Xinyu Liu","email":"","orcid":"","institution":"Guangzhou Power Supply Bureau Co., Ltd, China.","correspondingAuthor":false,"prefix":"","firstName":"Xinyu","middleName":"","lastName":"Liu","suffix":""},{"id":395105279,"identity":"1379ba91-592e-46c9-ad0c-f559a898d373","order_by":5,"name":"Haobo Shen","email":"","orcid":"","institution":"Guangzhou Power Supply Bureau Co., Ltd, China.","correspondingAuthor":false,"prefix":"","firstName":"Haobo","middleName":"","lastName":"Shen","suffix":""},{"id":395105280,"identity":"4139b501-672c-4658-af97-fcf5f70aa487","order_by":6,"name":"Song Fei","email":"","orcid":"","institution":"Hong Kong University of Science and Technology (Guangzhou)","correspondingAuthor":false,"prefix":"","firstName":"Song","middleName":"","lastName":"Fei","suffix":""},{"id":395105281,"identity":"ae0cc373-d5ae-4682-9b10-06d98fe0b792","order_by":7,"name":"Lei Zhu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAqklEQVRIiWNgGAWjYBACPgbGBmYGBhsQm42xgRgtbBAtaSAW0VoYGIBaDpOihb25+XNh2/nE+fMb2B7OIEoLz8EG45lttxM3HGNgN9xAlBaJxIZkXpAWoMMkHxClRf5hw2HetnOJ89uI1iLB2NjM23YgseEYUAtxDuNJbGbmOZdsvOFYYpskUd7nZz/++DNPmZ3s/ObDxyR7iNGCBIiLlVEwCkbBKBgFxAAA+KkurrZngRsAAAAASUVORK5CYII=","orcid":"","institution":"Hong Kong University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Lei","middleName":"","lastName":"Zhu","suffix":""}],"badges":[],"createdAt":"2024-12-27 07:08:39","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5719588/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5719588/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00371-025-03848-2","type":"published","date":"2025-03-11T15:58:25+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":78689083,"identity":"23fe83e1-0d74-4cac-b0e4-037397330f38","added_by":"auto","created_at":"2025-03-17 16:11:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":809579,"visible":true,"origin":"","legend":"","description":"","filename":"MSUMambaMultiScaleDefocusBlurDetectionUsingCrossScaleFusionandStateSpaceModels.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5719588/v1_covered_da7509c7-09eb-4fab-9417-25993e50ffc0.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"MSU-Mamba: Multi-Scale Defocus Blur Detection Using Cross-Scale Fusion and State Space Models","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":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Defocus Blur Detection, Multi-Scale Fusion, State Space Model, Cross-Scale Scanning, Image Segmentation","lastPublishedDoi":"10.21203/rs.3.rs-5719588/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5719588/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Defocus blur detection (DBD) plays a pivotal role in computer vision, serving as a fundamental step to enhance the performance of various downstream applications, such as image refocusing, depth estimation, and saliency detection. Despite recent advancements, existing methods often struggle in complex scenes with homogeneous regions, subtle blur transitions, and cluttered backgrounds. In this paper, we develop a novel approach (MSU-Mamba) to combine a multi-scale feature extraction with state-space modeling for boosting defocus blur detection. To do so, we develop a Multi-Scale Fusion (MSF) Block to integrate long-range dependency features across multiple scales to enhance feature representation. Moreover, in our MSF block, we devise a cross-scale token scanning mechanism into the original Mamba to better distinguish blurred and sharp regions. Comprehensive experiments conducted on benchmark datasets show that our MSU-Mamba outperforms state-of-the-art methods in terms of F-measure and MAE. The results validate our approach as a promising solution to the challenges of defocus blur detection and its application to downstream tasks.","manuscriptTitle":"MSU-Mamba: Multi-Scale Defocus Blur Detection Using Cross-Scale Fusion and State Space Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-30 10:05:19","doi":"10.21203/rs.3.rs-5719588/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-01-17T09:31:21+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-01-14T05:39:38+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-01-12T14:47:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"173450827369821690070633406434933540241","date":"2025-01-07T07:25:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"334338222639705938449402812650783739180","date":"2025-01-05T15:20:35+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-01-04T06:27:11+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-12-27T19:46:55+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-12-27T15:16:36+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Visual Computer","date":"2024-12-27T07:04:01+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"e03d96f7-163a-41dc-b2c4-89327e908189","owner":[],"postedDate":"December 30th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-03-17T16:04:50+00:00","versionOfRecord":{"articleIdentity":"rs-5719588","link":"https://doi.org/10.1007/s00371-025-03848-2","journal":{"identity":"the-visual-computer","isVorOnly":false,"title":"The Visual Computer"},"publishedOn":"2025-03-11 15:58:25","publishedOnDateReadable":"March 11th, 2025"},"versionCreatedAt":"2024-12-30 10:05:19","video":"","vorDoi":"10.1007/s00371-025-03848-2","vorDoiUrl":"https://doi.org/10.1007/s00371-025-03848-2","workflowStages":[]},"version":"v1","identity":"rs-5719588","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5719588","identity":"rs-5719588","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}