MuDupNet: Multitasking Dual-Threshold Pointer Network for Point Cloud Alignment

MuDupNet: Multitasking Dual-Threshold Pointer Network for Point Cloud Alignment | 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 MuDupNet: Multitasking Dual-Threshold Pointer Network for Point Cloud Alignment Yingjie Zhang, Keyuan Qiu, Zekai Ren, Shun Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4214295/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 Point cloud alignment is a core task in computer vision and robotics. To address the problems of inefficiency and insufficient interpretability often faced by existing methods when dealing with point clouds with complex local geometries, this paper proposes a model MuDupNet that combines traditional point cloud feature extraction methods and advanced deep learning techniques. This method employs a multi-task learning architecture, which is based on the regression of local geometric histogram features of the point cloud in the training phase, which enhances the deep interpretability of the network features and accuracy of the model, while a Dual-Threshold Pointer SVD (DPSVD) for point cloud alignment inference module is introduced to enhance the efficiency of the network in alignment. The experimental results show that the MuDupNet model exhibits excellent alignment accuracy and robustness on several standard datasets, especially when dealing with point cloud data with complex local geometries. Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Information technology Full Text Additional Declarations No competing interests reported. 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-4214295","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":291507470,"identity":"f7869791-e15b-4d0b-9ec6-3255f64faef7","order_by":0,"name":"Yingjie Zhang","email":"","orcid":"","institution":"Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Yingjie","middleName":"","lastName":"Zhang","suffix":""},{"id":291507471,"identity":"55bdfe01-a7c1-414d-8839-b5fd313a54fc","order_by":1,"name":"Keyuan Qiu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9klEQVRIiWNgGAWjYDACZgY2ICnBYMDe2PhAokJCTp4oLQdAWngOHzawOGNhbNhA2B6QFgYGA4m0NInKtopEMA8fMGdnv/b4Y5uFvTlDjoHEzXkSCYwNzA8f3cCjxbKZp9zgYJtE4s6GMwaGM7dJ5LEzsBkb5+DRYnCYJ03i4DaJBIODPQbJktskihkbeNikidFiD2QYHP47RyKx4QBBLezHQFoYNxxjS2yQbCBKCw+bxNl/EokbzjAfZpA4JmFs2EzIL+ePP5OoOFNnb3D/YfsPiZo6OXn25oeP8WlhYOAxQBNgxqscBNgfEFQyCkbBKBgFIxwAAE+4Tk79TrrxAAAAAElFTkSuQmCC","orcid":"","institution":"Shihezi University","correspondingAuthor":true,"prefix":"","firstName":"Keyuan","middleName":"","lastName":"Qiu","suffix":""},{"id":291507473,"identity":"db680cd6-585d-45a4-9061-eb6c4716e7aa","order_by":2,"name":"Zekai Ren","email":"","orcid":"","institution":"Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Zekai","middleName":"","lastName":"Ren","suffix":""},{"id":291507474,"identity":"3044d0f5-b7eb-463b-805a-65fa0b836fea","order_by":3,"name":"Shun Zhang","email":"","orcid":"","institution":"Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Shun","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2024-04-03 17:58:59","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4214295/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4214295/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":61456444,"identity":"a007c893-12e8-4916-99e2-c8fd896253d2","added_by":"auto","created_at":"2024-07-31 03:37:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":475487,"visible":true,"origin":"","legend":"","description":"","filename":"main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4214295/v1_covered_c7ef2d77-1110-43ec-9fbf-af8e15b185ef.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"MuDupNet: Multitasking Dual-Threshold Pointer Network for Point Cloud Alignment","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"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":"","lastPublishedDoi":"10.21203/rs.3.rs-4214295/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4214295/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Point cloud alignment is a core task in computer vision and robotics. To address the problems of inefficiency and insufficient interpretability often faced by existing methods when dealing with point clouds with complex local geometries, this paper proposes a model MuDupNet that combines traditional point cloud feature extraction methods and advanced deep learning techniques. This method employs a multi-task learning architecture, which is based on the regression of local geometric histogram features of the point cloud in the training phase, which enhances the deep interpretability of the network features and accuracy of the model, while a Dual-Threshold Pointer SVD (DPSVD) for point cloud alignment inference module is introduced to enhance the efficiency of the network in alignment. The experimental results show that the MuDupNet model exhibits excellent alignment accuracy and robustness on several standard datasets, especially when dealing with point cloud data with complex local geometries.","manuscriptTitle":"MuDupNet: Multitasking Dual-Threshold Pointer Network for Point Cloud Alignment","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-17 18:18:53","doi":"10.21203/rs.3.rs-4214295/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":"141b0dc8-fa32-4829-8437-471a53746a85","owner":[],"postedDate":"April 17th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":30708723,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":30708724,"name":"Physical sciences/Mathematics and computing/Information technology"}],"tags":[],"updatedAt":"2024-07-31T03:29:19+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-17 18:18:53","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4214295","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4214295","identity":"rs-4214295","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}