3D Human Pose Estimation Based on Conditional Dual-Branch Diffusion Model

3D Human Pose Estimation Based on Conditional Dual-Branch Diffusion Model | 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 Human Pose Estimation Based on Conditional Dual-Branch Diffusion Model Jinghua Li, Zhuowei Bai, Dehui Kong, Dongpan Chen, Qianxing Li, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4562542/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 09 Dec, 2024 Read the published version in Multimedia Systems → Version 1 posted 11 You are reading this latest preprint version Abstract Thanks to the development of 2D keypoint detectors, monocular 3D human pose estimation (HPE) via 2D-to-3D lifting approaches have achieved remarkable improvements. However, monocular 3D HPE is still a challenging problem due to the inherent depth ambiguities and occlusions. Recently, diffusion models have achieved great success in the field of image generation. Inspired by this, we transform 3D human pose estimation problem into a reverse diffusion process, and propose a dual-branch diffusion model that could fully explore the global and local correlations between joints. Furthermore, we propose conditional dual-branch diffusion model to enhance the performance of 3D human pose estimation, in which the joint-level semantic information are regarded as the condition of the diffusion model, and integrated into the joint-level representations of 2D pose to enhance the expression of joints. The proposed method is verified on two widely used datasets and the experimental results have demonstrated the superiority. Human pose estimation Diffusion model Dual-branch Joint semantics 1 Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 09 Dec, 2024 Read the published version in Multimedia Systems → Version 1 posted Editorial decision: Revision requested 05 Sep, 2024 Reviews received at journal 06 Aug, 2024 Reviews received at journal 22 Jul, 2024 Reviewers agreed at journal 22 Jul, 2024 Reviews received at journal 21 Jul, 2024 Reviewers agreed at journal 02 Jul, 2024 Reviewers agreed at journal 22 Jun, 2024 Reviewers invited by journal 17 Jun, 2024 Editor assigned by journal 14 Jun, 2024 Submission checks completed at journal 12 Jun, 2024 First submitted to journal 11 Jun, 2024 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-4562542","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":318517100,"identity":"e4c7bd68-f3fc-4f9d-ab12-98baeabc6a27","order_by":0,"name":"Jinghua Li","email":"","orcid":"","institution":"Beijing University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Jinghua","middleName":"","lastName":"Li","suffix":""},{"id":318517103,"identity":"c17bcff6-b66c-4b79-9b01-b96f6765292f","order_by":1,"name":"Zhuowei Bai","email":"","orcid":"","institution":"Beijing University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhuowei","middleName":"","lastName":"Bai","suffix":""},{"id":318517104,"identity":"afb95a4d-5d11-4d37-8e58-d5163cf77dc6","order_by":2,"name":"Dehui Kong","email":"","orcid":"","institution":"Beijing University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Dehui","middleName":"","lastName":"Kong","suffix":""},{"id":318517108,"identity":"89d44a1d-8aa2-4151-87d1-9791f2525a5a","order_by":3,"name":"Dongpan Chen","email":"","orcid":"","institution":"Beijing University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Dongpan","middleName":"","lastName":"Chen","suffix":""},{"id":318517110,"identity":"c827e8fa-66af-493d-89fd-f3cee785167a","order_by":4,"name":"Qianxing Li","email":"","orcid":"","institution":"Beijing University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Qianxing","middleName":"","lastName":"Li","suffix":""},{"id":318517111,"identity":"6384fb2a-ff89-4d8f-8e77-1bba461765db","order_by":5,"name":"Baocai Yin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAtElEQVRIiWNgGAWjYDACCQbGxww8YKYB0VqYjYFaJEjSwiYNpojWYnC7+Vl1gczhOgb25m0SDDV3iNBy55jZ7Rk8hyUYeI6VSTAce0aElhs5bLd5QFokcswkGBsOE6elGKxF/g0JWpghtvAQqUXyzjFj6Rk86ZJtPGnFFgnHiNDCd7v54efCHmt+fvbDG298qCFCi8IBIMHYw8DABuIlENbAwCDfACJ/EKN0FIyCUTAKRiwAANSWM3LAsQ5YAAAAAElFTkSuQmCC","orcid":"","institution":"Beijing University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Baocai","middleName":"","lastName":"Yin","suffix":""}],"badges":[],"createdAt":"2024-06-11 08:37:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4562542/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4562542/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00530-024-01569-5","type":"published","date":"2024-12-09T15:57:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":71552458,"identity":"fc0bf28f-ea02-4487-8be4-0d23242e93ab","added_by":"auto","created_at":"2024-12-16 16:06:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":766294,"visible":true,"origin":"","legend":"","description":"","filename":"3DHumanPoseEstimationBasedonConditional.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4562542/v1_covered_eb7cf1f5-a13a-4e06-8d98-8f5ed1e6433e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"3D Human Pose Estimation Based on Conditional Dual-Branch Diffusion Model","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":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Human pose estimation, Diffusion model, Dual-branch, Joint semantics 1","lastPublishedDoi":"10.21203/rs.3.rs-4562542/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4562542/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Thanks to the development of 2D keypoint detectors, monocular 3D human pose estimation (HPE) via 2D-to-3D lifting approaches have achieved remarkable improvements. However, monocular 3D HPE is still a challenging problem due to the inherent depth ambiguities and occlusions. Recently, diffusion models have achieved great success in the field of image generation. Inspired by this, we transform 3D human pose estimation problem into a reverse diffusion process, and propose a dual-branch diffusion model that could fully explore the global and local correlations between joints. Furthermore, we propose conditional dual-branch diffusion model to enhance the performance of 3D human pose estimation, in which the joint-level semantic information are regarded as the condition of the diffusion model, and integrated into the joint-level representations of 2D pose to enhance the expression of joints. The proposed method is verified on two widely used datasets and the experimental results have demonstrated the superiority.","manuscriptTitle":"3D Human Pose Estimation Based on Conditional Dual-Branch Diffusion Model","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-01 18:55:47","doi":"10.21203/rs.3.rs-4562542/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-09-06T01:14:22+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-08-07T01:31:08+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-07-22T14:44:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"262986214195878896164220868547337409049","date":"2024-07-22T14:25:22+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-07-21T10:21:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"307607008941326966354632877038486971927","date":"2024-07-02T05:25:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"77086171819321482459399213318359046708","date":"2024-06-22T09:37:21+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-06-17T05:05:58+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-06-14T09:16:52+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-06-12T16:12:05+00:00","index":"","fulltext":""},{"type":"submitted","content":"Multimedia Systems","date":"2024-06-11T08:36:13+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"5b178c62-d76c-4652-afa5-bf786c283067","owner":[],"postedDate":"July 1st, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-12-16T16:01:54+00:00","versionOfRecord":{"articleIdentity":"rs-4562542","link":"https://doi.org/10.1007/s00530-024-01569-5","journal":{"identity":"multimedia-systems","isVorOnly":false,"title":"Multimedia Systems"},"publishedOn":"2024-12-09 15:57:00","publishedOnDateReadable":"December 9th, 2024"},"versionCreatedAt":"2024-07-01 18:55:47","video":"","vorDoi":"10.1007/s00530-024-01569-5","vorDoiUrl":"https://doi.org/10.1007/s00530-024-01569-5","workflowStages":[]},"version":"v1","identity":"rs-4562542","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4562542","identity":"rs-4562542","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}