MultiPhys: Multi-Person Physics-aware 3D Motion Estimation
This work addresses the challenge of coherent and physically plausible multi-person motion estimation for applications in computer vision and animation, representing an incremental improvement over existing methods.
The paper tackles the problem of recovering multi-person 3D motion from monocular videos by introducing MultiPhys, a method that combines kinematic-based motion estimation with a physics simulator to produce physically compliant results, significantly reducing penetration and foot skating errors while maintaining competitive motion accuracy and smoothness.
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/).