CVPR2024

PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios

Jingbo Wang, Zhengyi Luo, Ye Yuan, Yixuan Li, Bo Dai

摘要

a) Rich body control with trajectory and terrain compatibility (b) Zero-shot animation recreation from real-world videos (3) Missing Frame (1) Upper Body Motion (2) Whole Body Motion (1) (2) (3) Upper Body Reference Whole Body Reference Frame 15 Frame 22 Frame 60 Time Steps Figure 1 . We showcase the effectiveness of our proposed framework in synthetic and real-world driving scenarios. Our framework excels at generating physically realistic animations that adhere to provided trajectories while offering extensive control over the upper and full body movements. Additionally, our framework demonstrates the remarkable ability to recreate pedestrian animations with occlusions from real-world videos in a zero-shot manner. These inherent capabilities make our framework a robust and versatile approach foron-demand pedestrian animation in driving scenarios.