{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/skeleton-graph-long-term-3d-motion-prediction","title":"Skeleton-Graph: Long-Term 3D Motion Prediction From 2D Observations Using Deep Spatio-Temporal Graph CNNs","arxiv_id":"2109.10257","date":"2021-09-21","proceeding":null,"authors":["Abduallah Mohamed","Huancheng Chen","Zhangyang Wang","Christian Claudel"],"abstract":"Several applications such as autonomous driving, augmented reality and virtual reality require a precise prediction of the 3D human pose. Recently, a new problem was introduced in the field to predict the 3D human poses from observed 2D poses. We propose Skeleton-Graph, a deep spatio-temporal graph CNN model that predicts the future 3D skeleton poses in a single pass from the 2D ones. Unlike prior works, Skeleton-Graph focuses on modeling the interaction between the skeleton joints by exploiting their spatial configuration. This is being achieved by formulating the problem as a graph structure while learning a suitable graph adjacency kernel. By the design, Skeleton-Graph predicts the future 3D poses without divergence in the long-term, unlike prior works. We also introduce a new metric that measures the divergence of predictions in the long term. Our results show an FDE improvement of at least 27% and an ADE of 4% on both the GTA-IM and PROX datasets respectively in comparison with prior works. Also, we are 88% and 93% less divergence on the long-term motion prediction in comparison with prior works on both GTA-IM and PROX datasets. Code is available at https://github.com/abduallahmohamed/Skeleton-Graph.git","url_abs":"https://arxiv.org/abs/2109.10257v2","url_pdf":"https://arxiv.org/pdf/2109.10257v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"skeleton-graph-long-term-3d-motion-prediction","repo_url":"https://github.com/abduallahmohamed/skeleton-graph","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"trajectory-prediction","task_name":"Trajectory Prediction"},{"task_slug":"motion-prediction","task_name":"motion prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/trajectory-prediction-on-gta-im-dataset","task":"Trajectory Prediction","dataset":"GTA-IM Dataset","model":"Skeleton-Graph","rank_in_archive_order":1,"of":1,"metrics":{"ADE":"192","FDE":"208","STB":"11"},"uses_additional_data":false},{"leaderboard":"/sota/trajectory-prediction-on-prox","task":"Trajectory Prediction","dataset":"PROX","model":"Skeleton-Graph","rank_in_archive_order":1,"of":1,"metrics":{"ADE":"280","FDE":"288","STB":"6"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}