Stacked AutoEncoder-based Compression of Point Cloud Geometry

Stacked AutoEncoder-based Compression of Point Cloud Geometry | 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 Stacked AutoEncoder-based Compression of Point Cloud Geometry Xuewei Cao, Wenbiao Zhou, Shuyu Yan, Genpei Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5665971/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 clouds have gained widespread application in various fields, but their high resolution often results in large data volumes, posing challenges for storage, transmission, and processing. Traditional 2D image or video compression methods are unsuitable due to the spatial irregularity and sparseness of point clouds. Inspired by the effectiveness of autoencoders in visual analysis tasks and image compression, this paper proposes a novel stacked autoencoder-based geometry compression method for point clouds. By transforming point clouds into Morton codes using a linear octree structure and further encoding them into integer sequences, the proposed method leverages stacked autoencoders to reduce the dimensions of these sequences, achieving both high reconstruction quality and high compression ratios. Experimental results demonstrate that our method outperforms many other geometry compression methods, especially for small-size point clouds. By increasing the coding depth of the linear octree, our approach can even achieve lossless compression results, showcasing its potential as an effective geometry compression technique for point clouds. point cloud compression deep learning linear octree stacked autoencoder Full Text 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-5665971","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":400112910,"identity":"919e75af-1e36-4047-8937-abe29b4f5e4e","order_by":0,"name":"Xuewei Cao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+UlEQVRIie3QsUrEQBCA4QkDm2aM7cjJ5RU2BM4mDzNBSHWFb3CRg6sCtmejr2Cl7UogNvcAKd3mWg8O5ApRN63I5uws9i+X+djZBQiF/mFpvDRmR8VUIXYgw5EZIVnTlXZ9XuVJrCoQOYJAP89zKtry7pRmAMeQqJYZ0xyjFdL7qz3ANOkl2l95SAymYt4oVHjypN1i+VkvOFn7brmuO84aUo48siPlQy8KybdZG624/GRyY9uBLMZJh6gNaXZjaiCix0jWqMjWJNq95kJLxdntxi4nPpKmb7v2g74W9zft1h6KIk1eLp/33sV+xDB8/B9AKBQKhX7rG9WFR8MQLsYtAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0001-9562-7601","institution":"Beijing Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Xuewei","middleName":"","lastName":"Cao","suffix":""},{"id":400112911,"identity":"8df4d068-735b-430c-8864-1840afc71142","order_by":1,"name":"Wenbiao Zhou","email":"","orcid":"","institution":"Beijing Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Wenbiao","middleName":"","lastName":"Zhou","suffix":""},{"id":400112912,"identity":"105bb08e-b793-42c4-ba1f-1be89df9ac8b","order_by":2,"name":"Shuyu Yan","email":"","orcid":"","institution":"Beijing Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Shuyu","middleName":"","lastName":"Yan","suffix":""},{"id":400112913,"identity":"62627b00-21fb-44e1-9b6f-a2f47e3d2afe","order_by":3,"name":"Genpei Liu","email":"","orcid":"","institution":"Beijing Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Genpei","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2024-12-18 04:40:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5665971/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5665971/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":79527527,"identity":"5a17fa40-a1a8-4997-96b2-9e284bbd8442","added_by":"auto","created_at":"2025-03-30 16:45:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1719674,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5665971/v1_covered_ec851d37-01d8-4ad4-9887-a1ddc351224d.pdf"}],"financialInterests":"","formattedTitle":"Stacked AutoEncoder-based Compression of Point Cloud Geometry","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":"point cloud compression, deep learning, linear octree, stacked autoencoder","lastPublishedDoi":"10.21203/rs.3.rs-5665971/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5665971/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003ePoint clouds have gained widespread application in various fields, but their high resolution often results in large data volumes, posing challenges for storage, transmission, and processing. Traditional 2D image or video compression methods are unsuitable due to the spatial irregularity and sparseness of point clouds. Inspired by the effectiveness of autoencoders in visual analysis tasks and image compression, this paper proposes a novel stacked autoencoder-based geometry compression method for point clouds. By transforming point clouds into Morton codes using a linear octree structure and further encoding them into integer sequences, the proposed method leverages stacked autoencoders to reduce the dimensions of these sequences, achieving both high reconstruction quality and high compression ratios. Experimental results demonstrate that our method outperforms many other geometry compression methods, especially for small-size point clouds. By increasing the coding depth of the linear octree, our approach can even achieve lossless compression results, showcasing its potential as an effective geometry compression technique for point clouds.\u003c/p\u003e","manuscriptTitle":"Stacked AutoEncoder-based Compression of Point Cloud Geometry","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-01-13 04:56:27","doi":"10.21203/rs.3.rs-5665971/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":"f5360003-70ce-4fb2-91a2-b09ef8a0ddac","owner":[],"postedDate":"January 13th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-03-30T16:36:56+00:00","versionOfRecord":[],"versionCreatedAt":"2025-01-13 04:56:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5665971","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5665971","identity":"rs-5665971","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}