核心概念
Introducing M3Act, a synthetic data generator for multi-view multi-group multi-person human atomic actions and group activities, facilitating human-centered tasks.
統計
M3Act improves the state-of-the-art MOTRv2 on DanceTrack dataset, moving from 10th to 2nd place.
M3Act contains 25 photometric 3D scenes, 104 HDRIs, 2200 human models, 384 animations, and 6 group activities.
引用
"The study of complex human interactions and group activities has become a focal point in human-centric computer vision."
"M3Act opens new research for controllable 3D group activity generation."