Geometrically Aware Transformer for Point Cloud Analysis

Geometrically Aware Transformer for Point Cloud Analysis | 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 Geometrically Aware Transformer for Point Cloud Analysis Siyuan Chen, Zhiwei Fang, Siyao Wan, Ting Zhou, Chunlin Chen, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5538442/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 13 May, 2025 Read the published version in Scientific Reports → Version 1 posted 6 You are reading this latest preprint version Abstract With the increasing use of 3D point cloud data in autonomous driving, robotic perception, and remote sensing, efficient and accurate point cloud analysis remains a critical challenge. This study presents PointGA, a lightweight Transformer-based model that enhances geometric perception for improved feature extraction and representation. First, PointGA expands the original 3D coordinates into various geometric information, introducing more prior knowledge into the network. Second, a trigonometric position encoding suitable for point clouds is designed, which effectively enhances the expressive capability of positional information and performs preliminary feature extraction through pooling layers, significantly improving the model's robustness across various tasks. Finally, a positional differential self-attention (PDA) mechanism with linear complexity is developed to optimize feature representation and achieve efficient computation. Experimental results demonstrate that PointGA achieves 87.6% overall accuracy on the ScanObjectNN dataset for classification and 66.2% mean intersection over union(mIoU) on the S3DIS Area 5 dataset for segmentation, outperforming existing methods. These findings highlight the model's capability to balance efficiency and accuracy, offering a promising solution for point cloud analysis tasks. Physical sciences/Mathematics and computing/Computational science 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: Published Journal Publication published 13 May, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Accepted 30 Apr, 2025 Reviews received at journal 21 Apr, 2025 Reviewers agreed at journal 21 Apr, 2025 Reviewers invited by journal 20 Apr, 2025 Submission checks completed at journal 11 Apr, 2025 First submitted to journal 08 Apr, 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-5538442","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":445787101,"identity":"9045f359-f1f5-4f22-b539-dab9872034e2","order_by":0,"name":"Siyuan Chen","email":"","orcid":"","institution":"Hunan Institute of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Siyuan","middleName":"","lastName":"Chen","suffix":""},{"id":445787105,"identity":"852af915-c2a9-459e-82a2-1091dac7b706","order_by":1,"name":"Zhiwei Fang","email":"","orcid":"","institution":"Hunan Institute of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhiwei","middleName":"","lastName":"Fang","suffix":""},{"id":445787108,"identity":"8c513e87-eec8-4d56-a575-3964af07935a","order_by":2,"name":"Siyao Wan","email":"","orcid":"","institution":"Hunan Institute of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Siyao","middleName":"","lastName":"Wan","suffix":""},{"id":445787110,"identity":"ed110b75-cfcc-4425-ab37-782339f1543a","order_by":3,"name":"Ting Zhou","email":"","orcid":"","institution":"Hunan Institute of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Ting","middleName":"","lastName":"Zhou","suffix":""},{"id":445787113,"identity":"c807f777-7517-4de2-9928-1a992f5b8616","order_by":4,"name":"Chunlin Chen","email":"","orcid":"","institution":"Hunan Institute of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Chunlin","middleName":"","lastName":"Chen","suffix":""},{"id":445787115,"identity":"1728b35d-5b59-47c9-ac74-e131b5b59a10","order_by":5,"name":"Meng Wang","email":"","orcid":"","institution":"Yueyang institute of Water Resources and Hydropower survey Planning and design Co., LTD.","correspondingAuthor":false,"prefix":"","firstName":"Meng","middleName":"","lastName":"Wang","suffix":""},{"id":445787118,"identity":"4ee20e1f-65be-4aff-aca0-a20865a39600","order_by":6,"name":"Qianming Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA80lEQVRIiWNgGAWjYBACPmYGhgNAmoeBgfkYA4MBWNAArxY2hBa2NJBiCcJaEEweMxBJhBZ25o0Hfu7YJmPOv+bb44KCujoG9uZtEgw1d/A4jK3gYO+Z2zyWM95uN55hcFiCgedYmQTDsWd4tPAYHOBtu81jcOPsNmkgW4JBIsdMgrHhMF4tB/+CtZx5BtRSJ8Eg/4awlsNgW873sAG1MANt4SGkha3gsCzYFjYzoJbDkm08acUWCcdwa+HnP7z549u22/YG5w8DHfanjp+f/fDGGx9qcGthgMeCRALUXhCRgE8DXAv/AfzKRsEoGAWjYOQCAACfS5fxQEVxAAAAAElFTkSuQmCC","orcid":"","institution":"Hunan Institute of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Qianming","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2024-11-28 01:23:31","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5538442/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5538442/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-00789-7","type":"published","date":"2025-05-13T15:57:39+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":83067954,"identity":"627aa89b-e9be-4097-b85c-10f4731a99b6","added_by":"auto","created_at":"2025-05-19 16:08:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1333628,"visible":true,"origin":"","legend":"","description":"","filename":"GeometricallyAwareTransformerforPointCloudAnalysis.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5538442/v1_covered_38e6f9bb-dd42-4984-8148-fb710fd1a8d4.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Geometrically Aware Transformer for Point Cloud Analysis","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":"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":"","lastPublishedDoi":"10.21203/rs.3.rs-5538442/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5538442/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"With the increasing use of 3D point cloud data in autonomous driving, robotic perception, and remote sensing, efficient and accurate point cloud analysis remains a critical challenge. This study presents PointGA, a lightweight Transformer-based model that enhances geometric perception for improved feature extraction and representation. First, PointGA expands the original 3D coordinates into various geometric information, introducing more prior knowledge into the network. Second, a trigonometric position encoding suitable for point clouds is designed, which effectively enhances the expressive capability of positional information and performs preliminary feature extraction through pooling layers, significantly improving the model's robustness across various tasks. Finally, a positional differential self-attention (PDA) mechanism with linear complexity is developed to optimize feature representation and achieve efficient computation. Experimental results demonstrate that PointGA achieves 87.6% overall accuracy on the ScanObjectNN dataset for classification and 66.2% mean intersection over union(mIoU) on the S3DIS Area 5 dataset for segmentation, outperforming existing methods. These findings highlight the model's capability to balance efficiency and accuracy, offering a promising solution for point cloud analysis tasks.","manuscriptTitle":"Geometrically Aware Transformer for Point Cloud Analysis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-23 07:15:12","doi":"10.21203/rs.3.rs-5538442/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Accepted","date":"2025-04-30T08:17:52+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-21T13:34:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"46204461716257915979425293122918081825","date":"2025-04-21T13:30:15+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-20T09:44:18+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-11T14:16:58+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-04-09T02:28:24+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":"12ad8a7d-5f3a-4a8f-8598-cdbad24a9114","owner":[],"postedDate":"April 23rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":47452311,"name":"Physical sciences/Mathematics and computing/Computational science"},{"id":47452312,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":47452313,"name":"Physical sciences/Mathematics and computing/Information technology"}],"tags":[],"updatedAt":"2025-05-19T16:04:06+00:00","versionOfRecord":{"articleIdentity":"rs-5538442","link":"https://doi.org/10.1038/s41598-025-00789-7","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-05-13 15:57:39","publishedOnDateReadable":"May 13th, 2025"},"versionCreatedAt":"2025-04-23 07:15:12","video":"","vorDoi":"10.1038/s41598-025-00789-7","vorDoiUrl":"https://doi.org/10.1038/s41598-025-00789-7","workflowStages":[]},"version":"v1","identity":"rs-5538442","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5538442","identity":"rs-5538442","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}