CVPR2023

Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion

Davis Rempe, Zhengyi Luo, Xue Bin Peng, Ye Yuan, Kris Kitani, Karsten Kreis, Sanja Fidler, Or Litany

Abstract

Figure 1. (Left) We propose TRACE, a trajectory diffusion model that enables user control through test-time guidance. (Right) Generated trajectories are passed to a novel physics-based humanoid controller (PACER), forming a closed-loop pedestrian animation system.