[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83419-en":3,"doc-seo-83419-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83419,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Pose-to-Biomechanics Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction","Recent advances in 3D human pose estimation enable markerless skeletal motion recovery, yet most models target geometric keypoint accuracy rather than biomechanical quantities needed for rehabilitation, sports science, ergonomics, and clinical movement analysis. This work introduces BioModule, a lightweight, estimator-agnostic temporal transformer plug-in that predicts biomechanical attributes from standard 17-joint 3D skeletons. A large aligned dataset, Human3.6Mplus, pairs Human3.6M video keypoints with biomechanical labels via anatomically verified coordinate correspondence to enable frame-accurate cross-modal supervision.","arXiv :2607 .08725v 1 [ cs .CV] 9 Jul 2026  \nPose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction  \nAyda Eghbalian and Kevin Desai  \nDepartment of Computer Science, University of Texas at San Antonio, One UTSA Circle, San Antonio, 78249, Texas, United States.  \nContributing authors: [ayda.eghbalian@utsa.edu](ayda.eghbalian@utsa.edu) ; [kevin.desai@utsa.edu](kevin.desai@utsa.edu) ;  \nAbstract  \nRecent progress in 3D human pose estimation has made markerless recovery of skeletal motion increasingly accurate and scalable. However, most pose estimators remain optimized for geometric keypoint accuracy, while many real-world applications in rehabilitation, sports science, ergonomics, and clinical movement analysis require biomechanical quantities that describe how the body moves, loads, and activates. In this work, we propose BioModule, a lightweight plug-in temporal transformer that attaches downstream of any 3D pose estimator and predicts biomechanical attributes from standard 17-joint 3D skeletons. BioModule is estimator-agnostic and requires no modification of the upstream pose model, enabling existing pose estimators to be extended toward physically interpretable motion analysis.  \nTo train and evaluate BioModule, we construct a large-scale aligned dataset pairing Human3.6M video and 3D keypoints with the biomechanical label space of Human3.6Mplus. We establish and verify anatomical correspondence between coordinate systems of the two datasets, enabling frame-accurate cross-modal supervision. Using this aligned supervision, BioModule predicts biomechanical quantities. We further benchmark BioModule across seven state-of-the-art 3D pose estimators, providing the first systematic analysis of how upstream pose estimation quality propagates to downstream biomechanical prediction fidelity. The results position BioModule as a compact, modular bridge between visionbased pose estimation and biomechanically meaningful human motion analysis.  \nThe complete source code and additional qualitative results are available at:[https:](https:)//[utsa-virlab.github.io/BioModule/](utsa-virlab.github.io/BioModule/)  \nKeywords: Human Pose Estimation, Vision-based biomechanics, Markerless biomechanics, Musculoskeletal model  \n1  \n1 Introduction  \n3D human pose estimation models have become increasingly effective at recovering geometric skeletons from images and videos, yet a gap remains between kinematic pose and the biomechanical quantities required for physically meaningful motion analysis. Existing pose estimation benchmarks commonly optimize for Mean Per Joint Position Error (MPJPE) and related geometric metrics without quantifying physiological correctness, including torques, ground reaction forces, or muscle activation signals, which are essential assets in rehabilitation, and clinical movement assessment.[1–6] .  \nBridging this gap has traditionally required marker based motion capture laboratories, force plates, and electromyography, instrumentation that is expensive, environment constrained, and difficult to scale to in the wild video. Recent markerless pipelines such as OpenCap [7] and BioPose [8] have demonstrated that video derived kinematics can seed inverse dynamics solvers, but they either require multi view calibrated capture or per subject optimization at inference, limiting their scalability. Meanwhile, body model approaches improve anatomical realism but do not expose the full musculoskeletal output space needed for biomechanical analysis [9, 10] . The result is that no existing method enables conversion or integration of the 3D skeleton output of standard pose estimations with a comprehensive biomechanical attributes without additional instrumentation.  \nIn this paper, we propose BioModule, a plug-in temporal transformer that attaches downstream of any 3D pose estimator and simultaneously predicts 17 biomechanical criteria across three tiers: kinematic, kinetic, and neuromuscular. These cr","cbCaivbOxL4J4Uix","https://ap.wps.com/l/cbCaivbOxL4J4Uix","pdf",2352876,3,1,23,"English","en",105,"# Introduction\n## BioModule: estimator-agnostic biomechanical prediction\n## Bridging pose and biomechanics\n## Aligned dataset construction and supervision\n## Cross-estimator benchmarking","[{\"question\":\"What problem does BioModule address in 3D pose estimation?\",\"answer\":\"Most 3D pose estimators optimize geometric keypoint metrics rather than biomechanical quantities like torques, ground reaction forces, and muscle activation signals needed for physically meaningful motion analysis.\"},{\"question\":\"How does BioModule connect to existing 3D pose estimators?\",\"answer\":\"BioModule is a lightweight temporal transformer plug-in attached downstream of any 3D pose estimator, requiring only a temporally ordered 17-joint 3D skeleton and making no changes to the upstream model.\"},{\"question\":\"How is the training supervision prepared for BioModule?\",\"answer\":\"The work constructs Human3.6Mplus by aligning Human3.6M 3D keypoints with biomechanical label spaces, establishing and verifying anatomical correspondence between the datasets’ coordinate systems for frame-accurate cross-modal supervision.\"}]",1784187470,58,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"pose-to-biomechanics-bridging-3d-human-pose-estimation-and-biomechanical-attribute-prediction","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/pose-to-biomechanics-bridging-3d-human-pose-estimation-and-biomechanical-attribute-prediction/83419/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does BioModule address in 3D pose estimation?","Question",{"text":75,"@type":76},"Most 3D pose estimators optimize geometric keypoint metrics rather than biomechanical quantities like torques, ground reaction forces, and muscle activation signals needed for physically meaningful motion analysis.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does BioModule connect to existing 3D pose estimators?",{"text":80,"@type":76},"BioModule is a lightweight temporal transformer plug-in attached downstream of any 3D pose estimator, requiring only a temporally ordered 17-joint 3D skeleton and making no changes to the upstream model.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the training supervision prepared for BioModule?",{"text":84,"@type":76},"The work constructs Human3.6Mplus by aligning Human3.6M 3D keypoints with biomechanical label spaces, establishing and verifying anatomical correspondence between the datasets’ coordinate systems for frame-accurate cross-modal supervision.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]