{"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/anypose-anytime-3d-human-pose-forecasting-via","title":"AnyPose: Anytime 3D Human Pose Forecasting via Neural Ordinary Differential Equations","arxiv_id":"2309.04840","date":"2023-09-09","proceeding":null,"authors":["Zixing Wang","Ahmed H. Qureshi"],"abstract":"Anytime 3D human pose forecasting is crucial to synchronous real-world human-machine interaction, where the term ``anytime\" corresponds to predicting human pose at any real-valued time step. However, to the best of our knowledge, all the existing methods in human pose forecasting perform predictions at preset, discrete time intervals. Therefore, we introduce AnyPose, a lightweight continuous-time neural architecture that models human behavior dynamics with neural ordinary differential equations. We validate our framework on the Human3.6M, AMASS, and 3DPW dataset and conduct a series of comprehensive analyses towards comparison with existing methods and the intersection of human pose and neural ordinary differential equations. Our results demonstrate that AnyPose exhibits high-performance accuracy in predicting future poses and takes significantly lower computational time than traditional methods in solving anytime prediction tasks.","url_abs":"https://arxiv.org/abs/2309.04840v1","url_pdf":"https://arxiv.org/pdf/2309.04840v1.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":[],"tasks":[{"task_slug":"human-pose-forecasting","task_name":"Human Pose Forecasting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/human-pose-forecasting-on-3dpw","task":"Human Pose Forecasting","dataset":"3DPW","model":"AnyPose1","rank_in_archive_order":5,"of":7,"metrics":{"Average MPJPE (mm) 1000 msec":"84.4"},"uses_additional_data":false},{"leaderboard":"/sota/human-pose-forecasting-on-amass","task":"Human Pose Forecasting","dataset":"AMASS","model":"AnyPose1","rank_in_archive_order":5,"of":11,"metrics":{"Average MPJPE (mm) 1000 msec":"91.7"},"uses_additional_data":false},{"leaderboard":"/sota/human-pose-forecasting-on-human36m","task":"Human Pose Forecasting","dataset":"Human3.6M","model":"AnyPose1","rank_in_archive_order":16,"of":33,"metrics":{"Average MPJPE (mm) @ 1000 ms":"128.2","Average MPJPE (mm) @ 400ms":"80.6"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}