3D-SDIS：Enhanced 3D Instance Segmentation through Spectral Fusion and Dual-Sphere Sampling

3D-SDIS：Enhanced 3D Instance Segmentation through Spectral Fusion and Dual-Sphere Sampling | 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 3D-SDIS：Enhanced 3D Instance Segmentation through Spectral Fusion and Dual-Sphere Sampling BingGe Cong, XiaoHong Wang, Xu Zhao, NingNing Zhang, TianShui Zhu, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6670823/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 03 Oct, 2025 Read the published version in The Visual Computer → Version 1 posted 9 You are reading this latest preprint version Abstract 3D instance segmentation is essential in applications such as autonomous driving, augmented reality, and robotics, where accurate identification of individual objects in complex point cloud data is required. Existing methods typically rely on feature learning in a single spatial domain and often fail in cases involving overlapping objects and sparse point distributions. To solve these problems, we propose 3D-SDIS, a multi-domain 3D instance segmentation network. It includes an FFT-Spatial Fusion Encoder (FSF Encoder) that uses the Fourier transform to convert spatial features into the frequency domain. This process reduces interference from redundant points and improves boundary localization. We also introduce an Offset Dual-Sphere Sampling Module (ODSS), which performs multi-view feature sampling based on both the original and offset sphere centers. It increases the receptive field and captures more geometric information. Experimental results on the ScanNetV2 (62.9) and S3DIS (61.0) datasets demonstrate the superiority of 3D-SDIS over state-of-the-art methods, particularly in handling overlapping instances and large planar structures. The source code and trained models are available at http://github.com/cbbbbg/3D-SDIS. Point cloud 3D Instance Segmentation Fourier transform Dual-Spherical Sampling Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 03 Oct, 2025 Read the published version in The Visual Computer → Version 1 posted Editorial decision: Revision requested 02 Aug, 2025 Reviews received at journal 23 Jul, 2025 Reviewers agreed at journal 03 Jul, 2025 Reviews received at journal 23 Jun, 2025 Reviewers agreed at journal 27 May, 2025 Reviewers invited by journal 19 May, 2025 Editor assigned by journal 16 May, 2025 Submission checks completed at journal 16 May, 2025 First submitted to journal 15 May, 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-6670823","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":458523421,"identity":"af4aee66-be7e-4e26-939f-22240cefe71a","order_by":0,"name":"BingGe Cong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDUlEQVRIie3RsUrDQBjA8e8IXJcPbr0Q8BkuBASxNK9yIZApFKEgnUqk0Cx5gIg+hI9wckOXomvEJaVDF4e6iJN4p4M4XOzocH/IEu5HvvsC4PP9wxir9e59Pj5ho+rnLR8iYbspEjBP2CjyhfAvIpQUEVnpTHTySAJKyeSCFjK83u97slqkKQT3zwiTqUuQ5ZXatTiesqiMK/u5Bmh+jpDPXCQAMxnyYhbelMQQJRHwNEJQWeUgFKTgKHR297TeVnYwBPY2SNCQCKUhHdjBAtIA0kHC+aaIW2WXXMatfDB30TQ5uxW5k6SPte5fP+yvXPeHw+UiHdXLbfcynzjJ7+T3RkziqPM+n8/nc/QJiX9XzAHLB+UAAAAASUVORK5CYII=","orcid":"","institution":"University of Shanghai for Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"BingGe","middleName":"","lastName":"Cong","suffix":""},{"id":458523422,"identity":"7ea82141-861c-40b3-a3e4-bf29c55111b6","order_by":1,"name":"XiaoHong Wang","email":"","orcid":"","institution":"University of Shanghai for Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"XiaoHong","middleName":"","lastName":"Wang","suffix":""},{"id":458523423,"identity":"8fc723ea-7b62-4654-bf74-7bb7c417485d","order_by":2,"name":"Xu Zhao","email":"","orcid":"","institution":"University of Shanghai for Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Xu","middleName":"","lastName":"Zhao","suffix":""},{"id":458523424,"identity":"f960b8dc-efcf-494f-82be-6e7ea6cf9313","order_by":3,"name":"NingNing Zhang","email":"","orcid":"","institution":"University of Shanghai for Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"NingNing","middleName":"","lastName":"Zhang","suffix":""},{"id":458523425,"identity":"b525d010-80db-43be-a491-6eec3dab8ff6","order_by":4,"name":"TianShui Zhu","email":"","orcid":"","institution":"University of Shanghai for Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"TianShui","middleName":"","lastName":"Zhu","suffix":""},{"id":458523426,"identity":"e298fafe-90e3-488e-9b60-5442ef6b0c9f","order_by":5,"name":"KaiHang Chen","email":"","orcid":"","institution":"University of Shanghai for Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"KaiHang","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2025-05-15 09:08:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6670823/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6670823/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00371-025-04186-z","type":"published","date":"2025-10-03T15:56:59+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":92883626,"identity":"ea42dcad-099d-42bb-b5d9-1542361da342","added_by":"auto","created_at":"2025-10-06 16:06:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1100899,"visible":true,"origin":"","legend":"","description":"","filename":"shougao.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6670823/v1_covered_92283046-760d-4ecd-9e2f-94c4bf65f6f7.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"3D-SDIS：Enhanced 3D Instance Segmentation through Spectral Fusion and Dual-Sphere Sampling","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":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Point cloud, 3D Instance Segmentation, Fourier transform, Dual-Spherical Sampling","lastPublishedDoi":"10.21203/rs.3.rs-6670823/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6670823/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e3D instance segmentation is essential in applications such as autonomous driving, augmented reality, and robotics, where accurate identification of individual objects in complex point cloud data is required. Existing methods typically rely on feature learning in a single spatial domain and often fail in cases involving overlapping objects and sparse point distributions. To solve these problems, we propose 3D-SDIS, a multi-domain 3D instance segmentation network. It includes an FFT-Spatial Fusion Encoder (FSF Encoder) that uses the Fourier transform to convert spatial features into the frequency domain. This process reduces interference from redundant points and improves boundary localization. We also introduce an Offset Dual-Sphere Sampling Module (ODSS), which performs multi-view feature sampling based on both the original and offset sphere centers. It increases the receptive field and captures more geometric information. Experimental results on the ScanNetV2 (62.9) and S3DIS (61.0) datasets demonstrate the superiority of 3D-SDIS over state-of-the-art methods, particularly in handling overlapping instances and large planar structures. The source code and trained models are available at http://github.com/cbbbbg/3D-SDIS.\u003c/p\u003e","manuscriptTitle":"3D-SDIS：Enhanced 3D Instance Segmentation through Spectral Fusion and Dual-Sphere Sampling","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-20 09:24:26","doi":"10.21203/rs.3.rs-6670823/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-08-02T07:05:36+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-23T09:58:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"125167311785466980307664506664162673793","date":"2025-07-03T07:30:44+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-24T02:02:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"60567142940500708683369101702795013101","date":"2025-05-28T02:17:57+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-05-19T05:18:32+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-17T02:39:08+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-16T13:14:38+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Visual Computer","date":"2025-05-15T09:00:07+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"81d0a259-2713-4c86-b7cb-fb5f20fb2735","owner":[],"postedDate":"May 20th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-10-06T15:59:25+00:00","versionOfRecord":{"articleIdentity":"rs-6670823","link":"https://doi.org/10.1007/s00371-025-04186-z","journal":{"identity":"the-visual-computer","isVorOnly":false,"title":"The Visual Computer"},"publishedOn":"2025-10-03 15:56:59","publishedOnDateReadable":"October 3rd, 2025"},"versionCreatedAt":"2025-05-20 09:24:26","video":"","vorDoi":"10.1007/s00371-025-04186-z","vorDoiUrl":"https://doi.org/10.1007/s00371-025-04186-z","workflowStages":[]},"version":"v1","identity":"rs-6670823","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6670823","identity":"rs-6670823","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}