Populate-A-Scene: Affordance-Aware Human Video Generation

Mengyi Shan, Zecheng He, Haoyu Ma, Felix Juefei-Xu,
Peizhao Zhang, Tingbo Hou, Ching-Yao Chuang
Meta GenAI
Preprint 2025.
Paper Supplementary

Main Human Video Results































Two-Person Video Results
















Multi-Prompt Video Results














Baseline Comparisons (Input, CogVideoX, Gen-3, Ours)