[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-513201-105":59,"doc-detail-513201-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","optimal-state-dynamics-estimation-for-physics-based-human-motion-capture-from-videos","Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos","","Human motion capture from monocular videos has improved, yet many methods still suffer temporal artifacts such as jitter and insufficient physical plausibility. Integrating physics via internal forces and exterior torques can reduce these issues, but existing PD-controller re-simulation approaches rely on imperfect physical models and heavy preprocessing of kinematics. This work introduces OSDCap, an online meta-PD simulation with neural Kalman filtering to balance kinematics and simulated dynamics, enabling accurate global trajectories and physically plausible poses.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/optimal-state-dynamics-estimation-for-physics-based-human-motion-capture-from-videos/513201/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/optimal-state-dynamics-estimation-for-physics-based-human-motion-capture-from-videos/513201.png","ImageObject",300,407,{"name":92,"@type":93},"Adam","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-15","2026-10-06",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",11,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does the paper address in monocular video motion capture?","Question",{"text":113,"@type":114},"It targets temporal artifacts like jittery motion and difficulty producing smooth, physically plausible motion from monocular inputs.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the proposed method incorporate physics into motion estimation?",{"text":118,"@type":114},"It uses a physics-based simulation driven by a meta-PD controller to predict internal joint torques and external reaction forces, then simulates motion accordingly.",{"name":120,"@type":111,"acceptedAnswer":121},"Why is the neural Kalman-filtering step important?",{"text":122,"@type":114},"The paper states it provides online supervision that balances shortcomings of noisy kinematics and simulated motion, improving both global trajectory accuracy and physical plausibility.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},513201,1791369219,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":19,"preview_urls":147},1374404737137,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","arXiv :2410 .07795v4 [ cs .CV] 14 May 2025  \nOptimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos  \nCuong Le 1 , Viktor Johansson 1 , Manon Kok2 and Bastian Wandt 1  \n1Department of Electrical Engineering, Linköping University, Sweden  \n2Delft Center for Systems and Control, Delft University of Technology, The Netherlands  \nFigure 1: OSDCap is an optimal-state dynamics estimation (cyan) based on two streams of input motion, a kinematics-based pose estimation from videos (top-left), and a physics-based simulation by a meta-PD controller (bottom-left) . The predicted motion is physically-plausible, contains reduced high-frequency noise, while retaining highly accurate global position.  \nAbstract  \nHuman motion capture from monocular videos has made significant progress in recent years. However, modern approaches often produce temporal artifacts, e.g.  \nin form of jittery motion and struggle to achieve smooth and physically plausible motions. Explicitly integrating physics, in form of internal forces and exterior torques, helps alleviating these artifacts. Current state-of-the-art approaches make use of an automatic PD controller to predict torques and reaction forces in order tore-simulate the input kinematics, i.e. the joint angles of a predefined skeleton. However, due to imperfect physical models, these methods often require simplifying assumptions and extensive preprocessing of the input kinematics to achieve good performance. To this end, we propose a novel method to selectively incorporate the physics models with the kinematics observations in an online setting, inspired by a neural Kalman-filtering approach. We develop a control loop as a meta-PD controller to predict internal joint torques and external reaction forces, followed by a physics-based motion simulation. A recurrent neural network is introduced to realize a Kalman filter that attentively balances the kinematics input and simulated motion, resulting in an optimal-state dynamics prediction. We show that this filtering step is crucial to provide an online supervision that helps balancing the shortcoming of the respective input motions, thus being important for not only capturing accurate global motion trajectories but also producing physically plausible human poses. The proposed approach excels in the physics-based human pose estimation task and demonstrates the physical plausibility of the predictive dynamics, compared to state of the art. The code is available on § .  \n38th Conference on Neural Information Processing Systems (NeurIPS 2024) .  \n1 Introduction  \nThree-dimensional human motion estimation is a long-standing and challenging research goal in computer vision, particularly in monocular scenarios due to inherent depth ambiguities. Previous approaches have incorporated kinematic priors, e.g. by enforcing smoothness, maintaining bone length constancy, or imposing symmetry constraints. However, due to inconsistencies of frame-wise predictions, these solutions do not necessarily lead to physically plausible motions. This has led to the emergence of a new research direction that combines traditional 3D motion estimation with physical models of the human skeleton. Instead of directly predicting a human pose, these approaches estimate the internal joint torques and exterior forces that drive the motion. Consequently, physics simulators are employed to obtain the resulting motion [37, 38, 8, 50, 21] .  \nHowever, since simulators are never perfect representations ofthe real world, they introduce inevitable errors, where the complex human body was never fully modelled, only approximation by rigid body dynamics [3] . Moreover, measurements, including “ground truth” recordings, are inherently noisy. To tackle these problems, we propose OSDCap, a state-aware architecture that combines a differentiable physical simulation with our novel neural Kalman filtering approach. Fig. 1 shows our reconstructed poses predicted from noisy kinemati","cbCaivbdLgY0R9D0","https://ap.wps.com/l/cbCaivbdLgY0R9D0","pdf",29075164,17,"English","# Abstract\n# 1 Introduction","[{\"question\":\"What problem does the paper address in monocular video motion capture?\",\"answer\":\"It targets temporal artifacts like jittery motion and difficulty producing smooth, physically plausible motion from monocular inputs.\"},{\"question\":\"How does the proposed method incorporate physics into motion estimation?\",\"answer\":\"It uses a physics-based simulation driven by a meta-PD controller to predict internal joint torques and external reaction forces, then simulates motion accordingly.\"},{\"question\":\"Why is the neural Kalman-filtering step important?\",\"answer\":\"The paper states it provides online supervision that balances shortcomings of noisy kinematics and simulated motion, improving both global trajectory accuracy and physical plausibility.\"}]","Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos | PDF",1791281642,43,[148,152,156,160],{"page_no":8,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/750b99c647bbb0ab2281a778bf533bcf.webp",983,1272,{"page_no":14,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/dfafdc2ba9d1a495ac9f68340161b9fe.webp",982,1270,{"page_no":81,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/cfec3d6cb238d91e26b93d1d864cefb3.webp",981,1269,{"page_no":19,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/a6f09fa386f8b31aaea60c02ba18441f.webp",980,1268]