Occlusion-aware heatmap generation for enhancing 3D human pose estimation in multi-person environments

Occlusion-aware heatmap generation for enhancing 3D human pose estimation in multi-person environments | 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 Occlusion-aware heatmap generation for enhancing 3D human pose estimation in multi-person environments Sanghyeon Lee, Jong Taek Lee This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3820469/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 20 Jun, 2025 Read the published version in The Visual Computer → Version 1 posted 7 You are reading this latest preprint version Abstract In multi-person 3D human pose estimation (HPE), the lack of diverse and accurate 3D pose datasets remains a critical challenge. Despite recent advancements in learning-based methods, real-world scenarios with varied environments and individuals often lead to data biases and sparse annotations, complicating the achievement of robust generalization in visual computing applications. While recent data augmentation methods have shown promise in enhancing the generalization of 3D HPE, the majority target single-person settings, leaving multi-person scenarios insufficiently covered. Our paper presents a novel data augmentation technique for multi-person 3D HPE. We refine the data evolution framework to generate new single-person 3D poses and then combine them into multi-person scenarios. Notably, our method generates occlusion-aware 2D heatmaps by considering camera positions, 3D poses, and joint-specific occlusion uncertainties, capturing the nuances of real-world pose challenges. Evaluations on well-known datasets, such as CMU Panoptic, Shelf, and Campus, demonstrate our method's effectiveness, especially in constrained data environments. The code and dataset are available at: https://github.com/hyeon0819/MPDA . 3D human pose estimation Data augmentation Multi-view multi-person Pose generation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 20 Jun, 2025 Read the published version in The Visual Computer → Version 1 posted Editorial decision: Accepted 29 May, 2025 Reviews received at journal 09 Jan, 2025 Reviewers agreed at journal 30 Dec, 2024 Reviewers invited by journal 06 Jan, 2024 Editor assigned by journal 29 Dec, 2023 Submission checks completed at journal 29 Dec, 2023 First submitted to journal 29 Dec, 2023 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-3820469","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":264565007,"identity":"155cff6c-7bfc-47f5-8e1d-2fadf0a34363","order_by":0,"name":"Sanghyeon Lee","email":"","orcid":"","institution":"Kyungpook National University","correspondingAuthor":false,"prefix":"","firstName":"Sanghyeon","middleName":"","lastName":"Lee","suffix":""},{"id":264565008,"identity":"1631c7fa-a32e-4ff0-a13e-8cd739898392","order_by":1,"name":"Jong Taek Lee","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7klEQVRIiWNgGAWjYBACxgYIbcAHZD+EcpgJazkA1MIGVGlIlBYwgGphkyRKC3N77+HXH2psjNnYm49VztxxmIG//QCzcQU+h/WcS7M4cCzNjI3nWNrNjWcOM0icSWBOPINPy4wcM4MDbIdt2CRyzG4+bDvMwHCDgflgA0Et//7bsMm//1YI0iJPhBbjBwfbDpixSfCwMW4EajEAaknEq6XnjBnD2b5kYzaeNGPJmW3pPIZnEpsN8WkxbO8x/lDxzc6wn/3ww4+9bdZycscPH5bEq6WBgU0CWYAHkSJwAHlg1HzAq2IUjIJRMApGAQDmSU7M6ze24QAAAABJRU5ErkJggg==","orcid":"","institution":"Kyungpook National University","correspondingAuthor":true,"prefix":"","firstName":"Jong","middleName":"Taek","lastName":"Lee","suffix":""}],"badges":[],"createdAt":"2023-12-29 09:14:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3820469/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3820469/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00371-025-04040-2","type":"published","date":"2025-06-20T15:57:33+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":85231337,"identity":"36ea1245-a928-4431-bae9-42bcfdcdfb64","added_by":"auto","created_at":"2025-06-23 16:06:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":7591873,"visible":true,"origin":"","legend":"","description":"","filename":"submission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3820469/v1_covered_cb69bbdf-3ffc-4a92-a72c-12c06670e1db.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Occlusion-aware heatmap generation for enhancing 3D human pose estimation in multi-person environments","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":"3D human pose estimation, Data augmentation, Multi-view multi-person, Pose generation","lastPublishedDoi":"10.21203/rs.3.rs-3820469/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3820469/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In multi-person 3D human pose estimation (HPE), the lack of diverse and accurate 3D pose datasets remains a critical challenge. Despite recent advancements in learning-based methods, real-world scenarios with varied environments and individuals often lead to data biases and sparse annotations, complicating the achievement of robust generalization in visual computing applications. While recent data augmentation methods have shown promise in enhancing the generalization of 3D HPE, the majority target single-person settings, leaving multi-person scenarios insufficiently covered. Our paper presents a novel data augmentation technique for multi-person 3D HPE. We refine the data evolution framework to generate new single-person 3D poses and then combine them into multi-person scenarios. Notably, our method generates occlusion-aware 2D heatmaps by considering camera positions, 3D poses, and joint-specific occlusion uncertainties, capturing the nuances of real-world pose challenges. Evaluations on well-known datasets, such as CMU Panoptic, Shelf, and Campus, demonstrate our method's effectiveness, especially in constrained data environments. The code and dataset are available at: https://github.com/hyeon0819/MPDA.","manuscriptTitle":"Occlusion-aware heatmap generation for enhancing 3D human pose estimation in multi-person environments","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-02 06:59:35","doi":"10.21203/rs.3.rs-3820469/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Accepted","date":"2025-05-29T17:59:38+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-01-09T15:06:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"264107837729862964611964238690519121708","date":"2024-12-30T07:46:48+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-01-06T07:40:48+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2023-12-29T23:18:41+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2023-12-29T17:01:13+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Visual Computer","date":"2023-12-29T09:01:21+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":"84c09674-eb82-47db-a2e0-91d193c8ece2","owner":[],"postedDate":"January 2nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-06-23T16:01:09+00:00","versionOfRecord":{"articleIdentity":"rs-3820469","link":"https://doi.org/10.1007/s00371-025-04040-2","journal":{"identity":"the-visual-computer","isVorOnly":false,"title":"The Visual Computer"},"publishedOn":"2025-06-20 15:57:33","publishedOnDateReadable":"June 20th, 2025"},"versionCreatedAt":"2024-01-02 06:59:35","video":"","vorDoi":"10.1007/s00371-025-04040-2","vorDoiUrl":"https://doi.org/10.1007/s00371-025-04040-2","workflowStages":[]},"version":"v1","identity":"rs-3820469","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3820469","identity":"rs-3820469","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}