Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

MultiPhys: Multi-Person Physics-aware 3D Motion Estimation

About

We introduce MultiPhys, a method designed for recovering multi-person motion from monocular videos. Our focus lies in capturing coherent spatial placement between pairs of individuals across varying degrees of engagement. MultiPhys, being physically aware, exhibits robustness to jittering and occlusions, and effectively eliminates penetration issues between the two individuals. We devise a pipeline in which the motion estimated by a kinematic-based method is fed into a physics simulator in an autoregressive manner. We introduce distinct components that enable our model to harness the simulator's properties without compromising the accuracy of the kinematic estimates. This results in final motion estimates that are both kinematically coherent and physically compliant. Extensive evaluations on three challenging datasets characterized by substantial inter-person interaction show that our method significantly reduces errors associated with penetration and foot skating, while performing competitively with the state-of-the-art on motion accuracy and smoothness. Results and code can be found on our project page (http://www.iri.upc.edu/people/nugrinovic/multiphys/).

Nicolas Ugrinovic, Boxiao Pan, Georgios Pavlakos, Despoina Paschalidou, Bokui Shen, Jordi Sanchez-Riera, Francesc Moreno-Noguer, Leonidas Guibas• 2024

Related benchmarks

TaskDatasetResultRank
3D Human Pose EstimationChi3D
Invalid Rate7.4
14
Human Motion Fidelity EvaluationMotionPercept-FLAME (val)
Accuracy56.72
10
Human Motion Fidelity EvaluationMotionPercept-MDM (val)
Accuracy0.5513
10
3D Human Pose EstimationHi4D--
8
Showing 4 of 4 rows

Other info

Follow for update