Enhanced Optical Flow Estimation via Multiscale Kernel Selection and Super-Resolution Integration

Enhanced Optical Flow Estimation via Multiscale Kernel Selection and Super-Resolution Integration | 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 Enhanced Optical Flow Estimation via Multiscale Kernel Selection and Super-Resolution Integration Haoxin Guo, Yifan Wang, Xiaobo Guo This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7161624/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 01 Dec, 2025 Read the published version in The Visual Computer → Version 1 posted 9 You are reading this latest preprint version Abstract Optical flow estimation, pivotal in computer vision, captures motion between adjacent frames. Traditional methods like RAFT suffer from limited feature capture and adaptability in weak texture regions. We propose a refined optical flow estimation network integrating multiscale kernel selection and super-resolution techniques. A parameter-free Swift 3D weighted attention mechanism dynamically adjusts feature importance, while a super-resolution module enhances fine-grained feature capture. A context network with multiscale kernel selectivity expands the receptive field, improving adaptability. Experimental results demonstrate significant accuracy improvements on datasets like Sintel and FlyingChairs, showcasing the method's effectiveness in complex scenes. Code location https://github.com/yifanna/PS3D-flow.git . optical flow estimation attention mechanism super-resolution kernel selection Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 01 Dec, 2025 Read the published version in The Visual Computer → Version 1 posted Editorial decision: Revision requested 15 Sep, 2025 Reviews received at journal 09 Sep, 2025 Reviews received at journal 09 Sep, 2025 Reviewers agreed at journal 20 Aug, 2025 Reviewers agreed at journal 20 Aug, 2025 Reviewers invited by journal 20 Aug, 2025 Editor assigned by journal 19 Jul, 2025 Submission checks completed at journal 19 Jul, 2025 First submitted to journal 18 Jul, 2025 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-7161624","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":502967992,"identity":"cd93eb1f-10bf-4dbb-a88d-a8b42cb681e0","order_by":0,"name":"Haoxin Guo","email":"","orcid":"","institution":"Changchun University Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Haoxin","middleName":"","lastName":"Guo","suffix":""},{"id":502967993,"identity":"acb50c21-af9a-4dc5-9d12-f737ad49fb2f","order_by":1,"name":"Yifan Wang","email":"","orcid":"","institution":"Changchun University","correspondingAuthor":false,"prefix":"","firstName":"Yifan","middleName":"","lastName":"Wang","suffix":""},{"id":502967994,"identity":"dfcc681b-6b80-4ff4-ab14-878f30742062","order_by":2,"name":"Xiaobo Guo","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAs0lEQVRIiWNgGAWjYFACHjApx8befoAkLQbGfDxnEkjTkjhPwsGAOA3yEbkHP/P8+ZPeJsGQwPCjYhthLYZnziVL87YZ5LZJNx5g7Dlzmwgt7T1mzLwNQC0yBxKYGduI0dLMY8bM88cgnU0iwYA4LfLsQFt42AwSiNdiwHMuWXJum7FhGzCQDxLlF/kZuQc/vPkjJy/f3n7wwY8KYmw5gMQ5gEMRmi0NRCkbBaNgFIyCEQ0A/SI25wtbuZ0AAAAASUVORK5CYII=","orcid":"","institution":"Changchun University Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Xiaobo","middleName":"","lastName":"Guo","suffix":""}],"badges":[],"createdAt":"2025-07-19 03:53:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7161624/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7161624/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00371-025-04198-9","type":"published","date":"2025-12-01T15:57:55+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":97724053,"identity":"6f6c6329-61c9-4daf-a01d-5d44f239335e","added_by":"auto","created_at":"2025-12-08 16:11:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":943402,"visible":true,"origin":"","legend":"","description":"","filename":"0719.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7161624/v1_covered_259e22a3-606d-4e45-a9f9-a012a80a7bc2.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhanced Optical Flow Estimation via Multiscale Kernel Selection and Super-Resolution Integration","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":"optical flow estimation, attention mechanism, super-resolution, kernel selection","lastPublishedDoi":"10.21203/rs.3.rs-7161624/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7161624/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eOptical flow estimation, pivotal in computer vision, captures motion between adjacent frames. Traditional methods like RAFT suffer from limited feature capture and adaptability in weak texture regions. We propose a refined optical flow estimation network integrating multiscale kernel selection and super-resolution techniques. A parameter-free Swift 3D weighted attention mechanism dynamically adjusts feature importance, while a super-resolution module enhances fine-grained feature capture. A context network with multiscale kernel selectivity expands the receptive field, improving adaptability. Experimental results demonstrate significant accuracy improvements on datasets like Sintel and FlyingChairs, showcasing the method's effectiveness in complex scenes. Code location \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://github.com/yifanna/PS3D-flow.git\u003c/span\u003e\u003cspan address=\"https://github.com/yifanna/PS3D-flow.git\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/p\u003e","manuscriptTitle":"Enhanced Optical Flow Estimation via Multiscale Kernel Selection and Super-Resolution Integration","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-28 05:35:39","doi":"10.21203/rs.3.rs-7161624/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-15T09:39:21+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-10T03:43:24+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-10T03:10:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"11239990245007343666976496842388326592","date":"2025-08-20T08:00:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"302138877388941004665997108126018724726","date":"2025-08-20T06:35:03+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-20T06:27:11+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-19T11:00:22+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-19T07:47:30+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Visual Computer","date":"2025-07-19T03:50:01+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":"f064ec3e-22ae-40ba-ab10-7ce47acf195c","owner":[],"postedDate":"August 28th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-12-08T16:06:02+00:00","versionOfRecord":{"articleIdentity":"rs-7161624","link":"https://doi.org/10.1007/s00371-025-04198-9","journal":{"identity":"the-visual-computer","isVorOnly":false,"title":"The Visual Computer"},"publishedOn":"2025-12-01 15:57:55","publishedOnDateReadable":"December 1st, 2025"},"versionCreatedAt":"2025-08-28 05:35:39","video":"","vorDoi":"10.1007/s00371-025-04198-9","vorDoiUrl":"https://doi.org/10.1007/s00371-025-04198-9","workflowStages":[]},"version":"v1","identity":"rs-7161624","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7161624","identity":"rs-7161624","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}