Enhancing Pure-Vision BEV 3D Perception with Hybrid Data-Feature Optimization

Enhancing Pure-Vision BEV 3D Perception with Hybrid Data-Feature Optimization | 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 Enhancing Pure-Vision BEV 3D Perception with Hybrid Data-Feature Optimization Aitong Mao, Beihai Tan, Rong Yu, Guoliang Cheng, Xiaoxu Wang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8898319/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 Bird’s eye view (BEV)-based approaches relying solely on cameras offer a cost-effective alternative to LiDAR-based solutions for 3D perception, attracting significant research attention. However, existing methods face limitations in data diversity, contextual modeling across multi-camera views, and multi-scale feature fusion. To address these challenges, this paper proposes HDO-BEV, a Hybrid Data-Feature Optimization-enhanced architecture for pure-vision BEV 3D perception. HDO-BEV integrates three novel modules: RandomFlip for data augmentation, HS-FPN for optimized multi-scale feature fusion, and ContextBlock for context enhancement. Experiments on the nuScenes-mini dataset demonstrate that HDO-BEV achieves 0.388 mAP and 0.472 NDS, outperforming the baseline SA-BEV by 0.9%. These results validate that targeted architectural enhancements can significantly advance pure-vision BEV 3D environmental sensing for scalable autonomous driving systems.The source code for this study is open-sourced at: https://github.com/zaixianbaipiao/Enhancing-Pure-Vision-BEV-3D-Perception-with-Hybrid-Data-Feature-Optimization [DOI: 10.5281/zenodo.18587515] Bird’s-eye view Data augmentation 3D object detection Multi-view fusion Semantic segmentation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 23 Apr, 2026 Reviews received at journal 30 Mar, 2026 Reviewers agreed at journal 23 Mar, 2026 Reviewers agreed at journal 02 Mar, 2026 Reviewers invited by journal 02 Mar, 2026 Editor assigned by journal 17 Feb, 2026 Submission checks completed at journal 17 Feb, 2026 First submitted to journal 17 Feb, 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-8898319","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":600440370,"identity":"e950e8d3-b6d6-4551-b6cd-d13c1dd4fe5b","order_by":0,"name":"Aitong Mao","email":"","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Aitong","middleName":"","lastName":"Mao","suffix":""},{"id":600440371,"identity":"1f652046-d185-48c7-9543-017722474621","order_by":1,"name":"Beihai Tan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAw0lEQVRIiWNgGAWjYBACAwkQWcHA2ACieYjTwgwkzwC1sJGkhbGNFC3m0v0HPxfOq5XdcL+B8cHbNgZ5c0JaLOccZpaeue248YZjDMyGc9sYDHc2EHLYjWQGad5txxKBWtikedsYEgwOENbC/Jt3DlgL+29itQANb6gB28JMlBbLGclm1jzHDhjPPJbYLDnnnIThBkJazCUSH9/mqamT7Tt8+OCHN2U28gRtgYLDQAxOABLEqQeCOqJVjoJRMApGwQgEAHFFQCbue0xkAAAAAElFTkSuQmCC","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Beihai","middleName":"","lastName":"Tan","suffix":""},{"id":600440372,"identity":"ca0054a7-5e2e-4551-aa67-bb0dd1bc4ed6","order_by":2,"name":"Rong Yu","email":"","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Rong","middleName":"","lastName":"Yu","suffix":""},{"id":600440373,"identity":"e08df0b8-0b4e-467f-b28a-36d35561914e","order_by":3,"name":"Guoliang Cheng","email":"","orcid":"","institution":"Southern University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Guoliang","middleName":"","lastName":"Cheng","suffix":""},{"id":600440374,"identity":"6ea8ad05-5ed4-4e64-9e8a-8dadfde4c69b","order_by":4,"name":"Xiaoxu Wang","email":"","orcid":"","institution":"South China Normal University","correspondingAuthor":false,"prefix":"","firstName":"Xiaoxu","middleName":"","lastName":"Wang","suffix":""},{"id":600440375,"identity":"9a8b3f2e-b626-476f-9040-0ea2481a38c7","order_by":5,"name":"Wuchang Zhong","email":"","orcid":"","institution":"Guangdong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Wuchang","middleName":"","lastName":"Zhong","suffix":""}],"badges":[],"createdAt":"2026-02-17 06:53:59","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8898319/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8898319/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104401832,"identity":"5e7b7a11-ec46-4be6-bc48-41cf013fea48","added_by":"auto","created_at":"2026-03-11 12:13:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2148487,"visible":true,"origin":"","legend":"","description":"","filename":"TheVisualComputer.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8898319/v1_covered_d1a44a98-5827-49c7-a8fe-5c250c35c133.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhancing Pure-Vision BEV 3D Perception with Hybrid Data-Feature Optimization","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":"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":"Bird’s-eye view , Data augmentation, 3D object detection, Multi-view fusion, Semantic segmentation","lastPublishedDoi":"10.21203/rs.3.rs-8898319/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8898319/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Bird’s eye view (BEV)-based approaches relying solely on cameras offer a cost-effective alternative to LiDAR-based solutions for 3D perception, attracting significant research attention. However, existing methods face limitations in data diversity, contextual modeling across multi-camera views, and multi-scale feature fusion. To address these challenges, this paper proposes HDO-BEV, a Hybrid Data-Feature Optimization-enhanced architecture for pure-vision BEV 3D perception. HDO-BEV integrates three novel modules: RandomFlip for data augmentation, HS-FPN for optimized multi-scale feature fusion, and ContextBlock for context enhancement. Experiments on the nuScenes-mini dataset demonstrate that HDO-BEV achieves 0.388 mAP and 0.472 NDS, outperforming the baseline SA-BEV by 0.9\\%. These results validate that targeted architectural enhancements can significantly advance pure-vision BEV 3D environmental sensing for scalable autonomous driving systems.The source code for this study is open-sourced at: https://github.com/zaixianbaipiao/Enhancing-Pure-Vision-BEV-3D-Perception-with-Hybrid-Data-Feature-Optimization [DOI: 10.5281/zenodo.18587515]","manuscriptTitle":"Enhancing Pure-Vision BEV 3D Perception with Hybrid Data-Feature Optimization","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-05 02:44:36","doi":"10.21203/rs.3.rs-8898319/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-04-23T04:16:11+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-30T14:34:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"291917632677110533355976863079677119033","date":"2026-03-23T12:35:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"213891043710141765166580454898216305285","date":"2026-03-02T11:17:37+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-02T06:28:44+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-17T16:36:49+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-17T14:36:09+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Visual Computer","date":"2026-02-17T06:43:38+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":"a24ce433-a501-46c4-8a3b-1dc3695a6b1e","owner":[],"postedDate":"March 5th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-03-05T02:44:36+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-05 02:44:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8898319","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8898319","identity":"rs-8898319","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}