RoCNet: 3D robust registration of point clouds using deep learning

RoCNet: 3D robust registration of point clouds using deep learning | 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 RoCNet: 3D robust registration of point clouds using deep learning Karim SLIMANI, Brahim Tamadazte, Catherine Achard This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4257894/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 01 Jul, 2024 Read the published version in Machine Vision and Applications → Version 1 posted 9 You are reading this latest preprint version Abstract This paper introduces a new method for 3D point cloud registration based on deep learning. The architecture is composed of three distinct blocs: (i) an encoder with a convolutional graph-based descriptor that encodes the immediate neighbourhood of each point and an attention mechanism that encodes the variations of the surface normals. Such descriptors are refined by highlighting attention between the points of the same set (source and target) and then between the points of the two sets. (ii) a matching process that estimates a matrix of correspondences using the Sinkhorn algorithm. (iii) Finally, the rigid transformation between the two point clouds is calculated by RANSAC using the best scores of the correspondence matrix. We conduct experiments on the ModelNet40 dataset and real-world Bunny dataset, and our proposed architecture shows very promising results, outperforming state-of-the-art methods in most of the simulated configurations Point Cloud Registration Deep Learning Attention Mechanism Pose Estimation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 01 Jul, 2024 Read the published version in Machine Vision and Applications → Version 1 posted Editorial decision: Revision requested 06 Jun, 2024 Reviews received at journal 06 Jun, 2024 Reviews received at journal 22 May, 2024 Reviewers agreed at journal 06 May, 2024 Reviewers agreed at journal 06 May, 2024 Reviewers invited by journal 06 May, 2024 Submission checks completed at journal 12 Apr, 2024 Editor assigned by journal 12 Apr, 2024 First submitted to journal 12 Apr, 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-4257894","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":290566777,"identity":"69a5de48-b4a7-4a7f-977b-228a59da12fb","order_by":0,"name":"Karim SLIMANI","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCklEQVRIiWNgGAWjYBACCSA+AMQybCBeQoUEAxtMir0BvxYeiJYzSFp4DuDWApYHk4xtSFK4tEi2n3146AZDHQ+f2OFnDx7Os7Dnkz7AJl2YY8fAI41djzRPusHhHIbDPGzSaeYGidskEtv4EtikZ25LZuDhS8CqRY4hjQGo5QBQS4KZBFBLAhsPA5s077YDDPY82B0mx/8MpKUOqCX9m0TiHAl7uBYeHFqkJcC2MAO15ABtaZBgbCOkRXIGyBYDkF9yyiQSjgH9wsPYbA30Cw8uLRLn05g/51TUycnPTt8m+aOmzl6+h/ng7cJtdnK4tECAAQqPsYGZARZTRANm0pSPglEwCkbBMAcANQdGGeALhXoAAAAASUVORK5CYII=","orcid":"","institution":"Sorbonne University","correspondingAuthor":true,"prefix":"","firstName":"Karim","middleName":"","lastName":"SLIMANI","suffix":""},{"id":290566778,"identity":"ef0fb5c3-2e71-4edc-a641-6e313ca29b33","order_by":1,"name":"Brahim Tamadazte","email":"","orcid":"","institution":"Sorbonne University","correspondingAuthor":false,"prefix":"","firstName":"Brahim","middleName":"","lastName":"Tamadazte","suffix":""},{"id":290566779,"identity":"36d5c2c3-e32b-49f5-bf81-1180fa94d456","order_by":2,"name":"Catherine Achard","email":"","orcid":"","institution":"Sorbonne University","correspondingAuthor":false,"prefix":"","firstName":"Catherine","middleName":"","lastName":"Achard","suffix":""}],"badges":[],"createdAt":"2024-04-12 12:53:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4257894/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4257894/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00138-024-01584-6","type":"published","date":"2024-07-01T19:39:32+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":61525060,"identity":"56b6ffcc-cba6-4073-9c25-c497341e47fd","added_by":"auto","created_at":"2024-07-31 19:39:38","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1182421,"visible":true,"origin":"","legend":"","description":"","filename":"rocnetmva.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4257894/v1_covered_586eacaa-bc02-4b4b-9164-8aea680c5177.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"RoCNet: 3D robust registration of point clouds using deep learning","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":"machine-vision-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mvap","sideBox":"Learn more about [Machine Vision and Applications](https://www.springer.com/journal/138)","snPcode":"138","submissionUrl":"https://submission.springernature.com/new-submission/138/3","title":"Machine Vision and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Point Cloud Registration, Deep Learning, Attention Mechanism, Pose Estimation","lastPublishedDoi":"10.21203/rs.3.rs-4257894/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4257894/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"This paper introduces a new method for 3D point cloud registration based on deep learning. The architecture is composed of three distinct blocs: (i) an encoder with a convolutional graph-based descriptor that encodes the immediate neighbourhood of each point and an attention mechanism that encodes the variations of the surface normals. Such descriptors are refined by highlighting attention between the points of the same set (source and target) and then between the points of the two sets. (ii) a matching process that estimates a matrix of correspondences using the Sinkhorn algorithm. (iii) Finally, the rigid transformation between the two point clouds is calculated by RANSAC using the best scores of the correspondence matrix. We conduct experiments on the ModelNet40 dataset and real-world Bunny dataset, and our proposed architecture shows very promising results, outperforming state-of-the-art methods in most of the simulated configurations","manuscriptTitle":"RoCNet: 3D robust registration of point clouds using deep learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-17 05:54:41","doi":"10.21203/rs.3.rs-4257894/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-06-06T20:21:20+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-06-06T14:46:14+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-05-22T15:31:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"238561957560951814914088264214734967172","date":"2024-05-07T02:14:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"338527590898289652557126879444752337283","date":"2024-05-06T22:56:52+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-05-06T20:14:23+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-04-12T14:09:48+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-04-12T14:09:48+00:00","index":"","fulltext":""},{"type":"submitted","content":"Machine Vision and Applications","date":"2024-04-12T12:52:10+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"machine-vision-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mvap","sideBox":"Learn more about [Machine Vision and Applications](https://www.springer.com/journal/138)","snPcode":"138","submissionUrl":"https://submission.springernature.com/new-submission/138/3","title":"Machine Vision and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"b58363d4-3323-4d0a-8712-b0b837457b4d","owner":[],"postedDate":"April 17th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-07-31T19:39:32+00:00","versionOfRecord":{"articleIdentity":"rs-4257894","link":"https://doi.org/10.1007/s00138-024-01584-6","journal":{"identity":"machine-vision-and-applications","isVorOnly":false,"title":"Machine Vision and Applications"},"publishedOn":"2024-07-01 19:39:32","publishedOnDateReadable":"July 1st, 2024"},"versionCreatedAt":"2024-04-17 05:54:41","video":"","vorDoi":"10.1007/s00138-024-01584-6","vorDoiUrl":"https://doi.org/10.1007/s00138-024-01584-6","workflowStages":[]},"version":"v1","identity":"rs-4257894","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4257894","identity":"rs-4257894","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}