Robust Local Feature Descriptor for 3D Point Cloud Analysis using Siamese Networks

Robust Local Feature Descriptor for 3D Point Cloud Analysis using Siamese Networks | 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 Robust Local Feature Descriptor for 3D Point Cloud Analysis using Siamese Networks Abdolqader Mollazehi Dashtook, Masoumeh Rezaei This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9452225/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 8 You are reading this latest preprint version Abstract Point cloud processing, as a growing research domain in machine vision, has gained increasing importance with the advancement of low-cost 3D sensors. Utilizing 3D point cloud data for tasks like 3D object detection and robotic localization entails challenges such as occlusion and clutter. This paper proposes a novel local feature descriptor leveraging deep learning techniques to extract precise and efficient geometric information from the surrounding environment of a point. By integrating T-Net and Siamese networks, the proposed method is capable of extracting consistent local features for points that are rigidly equivalent, thus providing high accuracy in matching 3D objects under challenging conditions. The method not only demonstrates outstanding performance in addressing existing challenges in 3D point cloud processing, such as noise and occlusion, but also exhibits remarkable ability to detect and precisely match 3D objects. Evaluation results using the Bologna and 3DMatch datasets show that the proposed method outperforms existing methods significantly in terms of precision, recall, and fragment matching recall, achieving an average fragment matching recall of 91.23%. The proposed approach has potential applications in various fields, including machine vision, image processing, and augmented reality. Physical sciences/Engineering Physical sciences/Mathematics and computing 3D Point Cloud 3D Object Detection Local Feature Descriptor Feature Matching Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 15 May, 2026 Reviewers agreed at journal 14 May, 2026 Reviewers agreed at journal 13 May, 2026 Reviewers invited by journal 06 May, 2026 Editor assigned by journal 06 May, 2026 Editor invited by journal 03 May, 2026 Submission checks completed at journal 24 Apr, 2026 First submitted to journal 24 Apr, 2026 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-9452225","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":639978240,"identity":"1c0bb08f-2329-4701-a47b-b17490f73d8d","order_by":0,"name":"Abdolqader Mollazehi Dashtook","email":"","orcid":"","institution":"University of Sistan and Baluchestan","correspondingAuthor":false,"prefix":"","firstName":"Abdolqader","middleName":"Mollazehi","lastName":"Dashtook","suffix":""},{"id":639978241,"identity":"5fc9fb7f-5616-4ef7-962d-1332562347c9","order_by":1,"name":"Masoumeh Rezaei","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIie3OIQvCQBTA8TcOZrlx9YLMTyDcEMTmVznLTPYFkQNhFsGqiN/Bj7DxQMthXjAowpJhNoOKBoMGb9oM94f3eOUHD8Bm+9+4/zySl11CGj8T6KhXYqw+RyzOUas7qWBC6GULbJQ4GBlIcxPKYKx5bzYOJfHiHLiWkGoT0VRIL+a9ZUYF8RQCZACpMhJWpNcb77YzVjweQ6iVE+oMPcWl4BQIdRFEOXEbpLriwVSHIl3EOQ10R5UQcjgd+4MaG+F+d7xsfX+NeDKRt5LHUADna2Cz2Wy2D90BmoVOt6xGRTEAAAAASUVORK5CYII=","orcid":"","institution":"University of Sistan and Baluchestan","correspondingAuthor":true,"prefix":"","firstName":"Masoumeh","middleName":"","lastName":"Rezaei","suffix":""}],"badges":[],"createdAt":"2026-04-17 19:09:06","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9452225/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9452225/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109296164,"identity":"5710c25f-c838-47c9-8fcd-0ae31c45503b","added_by":"auto","created_at":"2026-05-15 08:45:56","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":926306,"visible":true,"origin":"","legend":"","description":"","filename":"Main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9452225/v1_covered_86651d55-dbe2-42d0-bfb7-84a0aedc6837.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Robust Local Feature Descriptor for 3D Point Cloud Analysis using Siamese Networks","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"3D Point Cloud, 3D Object Detection, Local Feature Descriptor, Feature Matching","lastPublishedDoi":"10.21203/rs.3.rs-9452225/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9452225/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":" Point cloud processing, as a growing research domain in machine vision, has gained increasing importance with the advancement of low-cost 3D sensors. Utilizing 3D point cloud data for tasks like 3D object detection and robotic localization entails challenges such as occlusion and clutter. This paper proposes a novel local feature descriptor leveraging deep learning techniques to extract precise and efficient geometric information from the surrounding environment of a point. By integrating T-Net and Siamese networks, the proposed method is capable of extracting consistent local features for points that are rigidly equivalent, thus providing high accuracy in matching 3D objects under challenging conditions. The method not only demonstrates outstanding performance in addressing existing challenges in 3D point cloud processing, such as noise and occlusion, but also exhibits remarkable ability to detect and precisely match 3D objects. Evaluation results using the Bologna and 3DMatch datasets show that the proposed method outperforms existing methods significantly in terms of precision, recall, and fragment matching recall, achieving an average fragment matching recall of 91.23\\%. The proposed approach has potential applications in various fields, including machine vision, image processing, and augmented reality.","manuscriptTitle":"Robust Local Feature Descriptor for 3D Point Cloud Analysis using Siamese Networks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-14 05:17:10","doi":"10.21203/rs.3.rs-9452225/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"193378365141590261018978494507252866606","date":"2026-05-15T14:09:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"99141386243299757844469992388259209678","date":"2026-05-14T07:18:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"41883332287752021463338230012660869754","date":"2026-05-13T20:07:03+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-05-06T04:52:37+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-06T04:40:25+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-05-04T03:44:02+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-24T18:37:10+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-04-24T16:15:13+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"9822fe41-98a6-4f4e-82b8-f7872b650d06","owner":[],"postedDate":"May 14th, 2026","published":true,"recentEditorialEvents":[{"type":"reviewerAgreed","content":"193378365141590261018978494507252866606","date":"2026-05-15T14:09:40+00:00","index":96,"fulltext":""},{"type":"reviewerAgreed","content":"99141386243299757844469992388259209678","date":"2026-05-14T07:18:07+00:00","index":94,"fulltext":""},{"type":"reviewerAgreed","content":"41883332287752021463338230012660869754","date":"2026-05-13T20:07:03+00:00","index":91,"fulltext":""},{"type":"reviewersInvited","content":"57","date":"2026-05-06T04:52:37+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-06T04:40:25+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-05-04T03:44:02+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":68114599,"name":"Physical sciences/Engineering"},{"id":68114600,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-05-14T05:17:10+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-14 05:17:10","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9452225","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9452225","identity":"rs-9452225","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}