Deeply interactive pillars: Achieve advanced feature enhancement in 3D point clouds with deep interactions

Deeply interactive pillars: Achieve advanced feature enhancement in 3D point clouds with deep interactions | 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 Deeply interactive pillars: Achieve advanced feature enhancement in 3D point clouds with deep interactions 玲玲 施, 静 陈 This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6019369/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 The pillar-based feature learning mode demonstrates significant efficiency in 3D object detection. However, its aggressive downsampling operation results in the loss of explicit geometric cues, which adversely affects the model's ability to understand small target objects. Additionally, during the Pillar Feature Encoding (PFE) process, the 3D object detector encounters issues such as high-dimensional information loss and uneven numerical distribution, which hinder the improvement of model performance and quantification potential. To address these challenges, we introduce a novel method called Deeply Interactive Pillars (DIP). First, we propose a self-supplying dual token mechanism to facilitate global feature interaction. By incorporating spatial tokens and semantic tokens, the model enhances efficient interaction across global features, and the synergy between these tokens improves the model's ability to represent small targets in complex scenarios. Second, we design a new feature fusion module, the 3D Dual-Pool Attention Fusion Module (DP-AF), to refine the max-pooling operation in PointPillars. The DP-AF module integrates the benefits of double pooling and the Squeeze-and-Excitation (SE) mechanism, effectively enhancing the important information within the feature map of 3D point cloud data.Extensive experiments on the KITTI dataset validate the superior performance of our proposed DI-Pillar method. In pedestrian and cyclist detection tasks, DI-Pillar achieves accuracy rates of 59.85%, 53.30%, and 48.12% for pedestrians, and 89.07%, 67.70%, and 63.45% for cyclists, across the three difficulty levels of easy, medium, and hard, respectively. These results demonstrate the effectiveness and robustness of the proposed method. autonomous driving point cloud detection 3d object detection feature mining Full Text Additional Declarations No competing interests reported. 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-6019369","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":415264906,"identity":"b9b3491d-387b-4e4b-b385-d462dc4894a8","order_by":0,"name":"玲玲 施","email":"","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"玲玲","middleName":"","lastName":"施","suffix":""},{"id":415264907,"identity":"c4570162-bce7-4e75-8f6b-e71a942b966e","order_by":1,"name":"静 陈","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6klEQVRIiWNgGAWjYBACxgYeIGlgU88PJCECxGkpSEuQbABqOUCMFgYGkJYPhxMMDhCrhbn97MHHBQbMecbnF2+T/sBgI7vhAPOzB3gd1pOXbDzDgK3Y7MazMokDDGnGGw6wmRvg1TKDx0yax4CHcduNM2ZALYcTNxzgYZMgoMX8N4+BBOPmGWAt/4nSYsbMY2CQuIG/B6TlABFaenKMgQ5LMJa4wVZsccYg2XjmYTYzvFoM288Yfub581+Ov//wxhsVFXayfcebn+HX0gBjSSQwQBIAMz71QCAPZ/EfIKB0FIyCUTAKRiwAAEVfSZ4dOS10AAAAAElFTkSuQmCC","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":true,"prefix":"","firstName":"静","middleName":"","lastName":"陈","suffix":""}],"badges":[],"createdAt":"2025-02-13 04:08:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6019369/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6019369/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":78190539,"identity":"f7b2bdcc-b3a7-4502-9139-3581780b1f72","added_by":"auto","created_at":"2025-03-10 19:50:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2945761,"visible":true,"origin":"","legend":"","description":"","filename":"DIP.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6019369/v1_covered_55d8efdc-ab9a-4b06-9be6-03247b3ebe6c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Deeply interactive pillars: Achieve advanced feature enhancement in 3D point clouds with deep interactions","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":"autonomous driving, point cloud detection, 3d object detection, feature mining","lastPublishedDoi":"10.21203/rs.3.rs-6019369/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6019369/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe pillar-based feature learning mode demonstrates significant efficiency in 3D object detection. However, its aggressive downsampling operation results in the loss of explicit geometric cues, which adversely affects the model's ability to understand small target objects. Additionally, during the Pillar Feature Encoding (PFE) process, the 3D object detector encounters issues such as high-dimensional information loss and uneven numerical distribution, which hinder the improvement of model performance and quantification potential. To address these challenges, we introduce a novel method called Deeply Interactive Pillars (DIP). First, we propose a self-supplying dual token mechanism to facilitate global feature interaction. By incorporating spatial tokens and semantic tokens, the model enhances efficient interaction across global features, and the synergy between these tokens improves the model's ability to represent small targets in complex scenarios. Second, we design a new feature fusion module, the 3D Dual-Pool Attention Fusion Module (DP-AF), to refine the max-pooling operation in PointPillars. The DP-AF module integrates the benefits of double pooling and the Squeeze-and-Excitation (SE) mechanism, effectively enhancing the important information within the feature map of 3D point cloud data.Extensive experiments on the KITTI dataset validate the superior performance of our proposed DI-Pillar method. In pedestrian and cyclist detection tasks, DI-Pillar achieves accuracy rates of 59.85%, 53.30%, and 48.12% for pedestrians, and 89.07%, 67.70%, and 63.45% for cyclists, across the three difficulty levels of easy, medium, and hard, respectively. These results demonstrate the effectiveness and robustness of the proposed method.\u003c/p\u003e","manuscriptTitle":"Deeply interactive pillars: Achieve advanced feature enhancement in 3D point clouds with deep interactions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-02-17 06:51:56","doi":"10.21203/rs.3.rs-6019369/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":"57f9ce06-afd6-4594-ba15-2254e18ca77b","owner":[],"postedDate":"February 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-03-10T19:26:12+00:00","versionOfRecord":[],"versionCreatedAt":"2025-02-17 06:51:56","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6019369","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6019369","identity":"rs-6019369","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}