Learned Neural Physics Simulation for Articulated 3D Human Pose Reconstruction

Misha Andriluka*, Baruch Tabanpour, Daniel Freeman, Cristian Sminchisescu ;

"We propose a novel neural network approach to model the dynamics of articulated human motion with contact. Our goal is to develop a faster and more convenient alternative to traditional physics simulators for use in computer vision tasks such as human motion reconstruction from video. To that end we introduce a training procedure and model components that support the construction of a recurrent neural architecture to accurately learn to simulate articulated rigid body dynamics. Our neural architecture (LARP) supports features typically found in traditional physics simulators, such as modeling of joint motors, variable dimensions of body parts, contact between body parts and objects, yet it is differentiable, and an order of magnitude faster than traditional systems when multiple simulations are run in parallel. To demonstrate the value of our approach we use it as a drop-in replacement for a state-of-the-art classical non-differentiable simulator in an existing video-based 3D human pose reconstruction framework [?] and show comparable or better accuracy."