PEDRA: Evaluating the Realism of Pedestrian Dynamics in Video Generation
Researchers have developed a new evaluation protocol called PEDRA to assess the realism of pedestrian dynamics in videos generated by AI models. This method aims to test how well text-to-video and image-to-video models can simulate multi-agent interactions, moving beyond single-subject realism. While leading models show promising capabilities in generating plausible crowd behavior, the evaluation also identified limitations in their physical consistency, such as issues with merging and disappearing pedestrians. AI
IMPACT This benchmark could drive improvements in AI's ability to simulate realistic human interactions in generated videos.