SBAHGNet:3D Human Pose Estimation via Skeleton-Biased Attention and High-Frequency Enhanced Graph Convolution

SBAHGNet:3D Human Pose Estimation via Skeleton-Biased Attention and High-Frequency Enhanced Graph Convolution | 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 SBAHGNet:3D Human Pose Estimation via Skeleton-Biased Attention and High-Frequency Enhanced Graph Convolution Yu Wang, Jiaqiu Ai, Xinyu Sun, Yong Zhang, Jinyang Huang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8548943/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Monocular 3D human pose estimation is challenged by depth ambiguity and complex articulation, which complicate feature modeling and demand robust spatio-temporal representations. Although existing methods have advanced spatio-temporal modeling, limitations remain: graph convolutional network (GCN) exhibits low-pass behavior that, as depth increases, attenuates high-frequency geometric details in joint trajectories and thus degrades depth accuracy; and standard self-attention does not explicitly encode skeletal topology, resulting in indirect modeling of bone connectivity. To address these issues, we propose SBAHGNet, a dual-branch spatio-temporal feature-fusion network. In the GCN branch, a Multi-Scale High-Frequency Enhancement (MSHFE) module—applied after feature aggregation-recovers high-frequency geometric cues lost to GCN smoothing, improving fine-grained depth representation. In the attention branch, a Skeletal-Biased Attention (SBA) module injects a learnable skeletal bias into spatial attention to explicitly encode skeletal topology and strengthen structural modeling. Complementary features from both branches are adaptively fused for final 3D pose regression. Extensive experiments on Human3.6M and MPI-INF-3DHP validate our approach. With detected 2D keypoints, SBAHGNet attains 37.24 mm MPJPE (P1) and 31.57 mm PA-MPJPE (P2) on Human3.6M (12.38 mm with ground-truth 2D), and 13.83 mm MPJPE, 99.02% PCK@150mm, and 88.22 AUC on MPI-INF-3DHP. With only 18.3M parameters, the model achieves a favorable accuracy–efficiency trade-off and outperforms many comparable methods. Monocular 3D human pose estimation Spatio-temporal fusion Graph convolutional network Skeletal-Biased Attention High-frequency enhancement Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 10 Apr, 2026 Reviews received at journal 20 Mar, 2026 Reviewers agreed at journal 09 Feb, 2026 Reviewers invited by journal 09 Feb, 2026 Editor assigned by journal 09 Jan, 2026 Submission checks completed at journal 09 Jan, 2026 First submitted to journal 08 Jan, 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-8548943","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":589080748,"identity":"43588137-9002-451e-9b49-364a71f9a75e","order_by":0,"name":"Yu Wang","email":"","orcid":"","institution":"Hefei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Wang","suffix":""},{"id":589080749,"identity":"d0f2cbb6-a6c2-4e3c-8c9a-226dfd96da46","order_by":1,"name":"Jiaqiu Ai","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABC0lEQVRIie3OsUrDQBzH8X8JXBz+tetBbHyFKwfBIvZZchxkSl2E4iSBwGWJDyAIvoabFwLtUuoquFi6drCLKCh4CQhSuNrR4b7jn/vwOwCX6z/mQawBKBA/n71usrA90r3IIU6Tzk3GAf8kP4U0jbzuPqRXwFK/T06EokmyOrtn4gG86hlhdG4jtIa4KhdUKFzN+HjORAlEniLIC+uMIbqrDPGTOBirT0MwChC0yCziuFn5agikLBiqZqX3tpMwQ+p25SCNgk5LkOwkg4YcLShXOJWDa8V4WRM+vGXSSsLHudysJ1f9uyKvXj4U6xdFvnxaX46sBABjAPL74LUftr43+XqLuFwul2urb0StVw3fmsNvAAAAAElFTkSuQmCC","orcid":"","institution":"Hefei University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Jiaqiu","middleName":"","lastName":"Ai","suffix":""},{"id":589080750,"identity":"00542c9b-8eed-4d5c-83fa-c168a0c19e9c","order_by":2,"name":"Xinyu Sun","email":"","orcid":"","institution":"Hefei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Xinyu","middleName":"","lastName":"Sun","suffix":""},{"id":589080751,"identity":"ec5ecd94-b959-48d8-b367-74b28542b15e","order_by":3,"name":"Yong Zhang","email":"","orcid":"","institution":"Hefei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Yong","middleName":"","lastName":"Zhang","suffix":""},{"id":589080752,"identity":"ed8dae38-4627-465a-a74d-96a918869a78","order_by":4,"name":"Jinyang Huang","email":"","orcid":"","institution":"Hefei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Jinyang","middleName":"","lastName":"Huang","suffix":""}],"badges":[],"createdAt":"2026-01-08 08:38:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8548943/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8548943/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":103056292,"identity":"6fd36221-dee6-4c56-ab86-6f419202d363","added_by":"auto","created_at":"2026-02-20 09:04:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1008477,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8548943/v1_covered_55c1ab6b-4ce8-43d3-a419-ac420b15156a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"SBAHGNet:3D Human Pose Estimation via Skeleton-Biased Attention and High-Frequency Enhanced Graph Convolution","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":"machine-vision-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mvap","sideBox":"Learn more about [Machine Vision and Applications](https://www.springer.com/journal/138)","snPcode":"138","submissionUrl":"https://submission.springernature.com/new-submission/138/3","title":"Machine Vision and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Monocular 3D human pose estimation, Spatio-temporal fusion, Graph convolutional network, Skeletal-Biased Attention, High-frequency enhancement","lastPublishedDoi":"10.21203/rs.3.rs-8548943/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8548943/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMonocular 3D human pose estimation is challenged by depth ambiguity and complex articulation, which complicate feature modeling and demand robust spatio-temporal representations. Although existing methods have advanced spatio-temporal modeling, limitations remain: graph convolutional network (GCN) exhibits low-pass behavior that, as depth increases, attenuates high-frequency geometric details in joint trajectories and thus degrades depth accuracy; and standard self-attention does not explicitly encode skeletal topology, resulting in indirect modeling of bone connectivity. To address these issues, we propose SBAHGNet, a dual-branch spatio-temporal feature-fusion network. In the GCN branch, a Multi-Scale High-Frequency Enhancement (MSHFE) module\u0026mdash;applied after feature aggregation-recovers high-frequency geometric cues lost to GCN smoothing, improving fine-grained depth representation. In the attention branch, a Skeletal-Biased Attention (SBA) module injects a learnable skeletal bias into spatial attention to explicitly encode skeletal topology and strengthen structural modeling. Complementary features from both branches are adaptively fused for final 3D pose regression. Extensive experiments on Human3.6M and MPI-INF-3DHP validate our approach. With detected 2D keypoints, SBAHGNet attains 37.24 mm MPJPE (P1) and 31.57 mm PA-MPJPE (P2) on Human3.6M (12.38 mm with ground-truth 2D), and 13.83 mm MPJPE, 99.02% PCK@150mm, and 88.22 AUC on MPI-INF-3DHP. With only 18.3M parameters, the model achieves a favorable accuracy\u0026ndash;efficiency trade-off and outperforms many comparable methods.\u003c/p\u003e","manuscriptTitle":"SBAHGNet:3D Human Pose Estimation via Skeleton-Biased Attention and High-Frequency Enhanced Graph Convolution","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-11 23:39:21","doi":"10.21203/rs.3.rs-8548943/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-10T14:16:01+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-20T16:43:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"66831599193876153403817656037177270400","date":"2026-02-09T16:23:01+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-09T15:58:47+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-09T05:37:29+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-09T05:36:06+00:00","index":"","fulltext":""},{"type":"submitted","content":"Machine Vision and Applications","date":"2026-01-08T08:18:04+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"machine-vision-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mvap","sideBox":"Learn more about [Machine Vision and Applications](https://www.springer.com/journal/138)","snPcode":"138","submissionUrl":"https://submission.springernature.com/new-submission/138/3","title":"Machine Vision and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"d4d1d221-a70d-41bc-99c9-fe952a4f5148","owner":[],"postedDate":"February 11th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-30T03:08:32+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-11 23:39:21","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8548943","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8548943","identity":"rs-8548943","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}