M3Act: Learning from Synthetic Human Group Activities

TL;DR

M3Act is a synthetic dataset generator for multi-view, multi-group human activities that enhances human activity recognition models and enables new research in controllable 3D group activity generation.

Contribution

We introduce M3Act, a photorealistic synthetic dataset for multi-person and multi-group activities, improving model performance and enabling new research avenues.

Findings

M3Act improves the MOTRv2 performance on DanceTrack from 10th to 2nd place.

Synthetic data from M3Act reduces reliance on costly real-world datasets.

M3Act enables controllable 3D group activity generation with new metrics and baselines.

Abstract

The study of complex human interactions and group activities has become a focal point in human-centric computer vision. However, progress in related tasks is often hindered by the challenges of obtaining large-scale labeled datasets from real-world scenarios. To address the limitation, we introduce M3Act, a synthetic data generator for multi-view multi-group multi-person human atomic actions and group activities. Powered by Unity Engine, M3Act features multiple semantic groups, highly diverse and photorealistic images, and a comprehensive set of annotations, which facilitates the learning of human-centered tasks across single-person, multi-person, and multi-group conditions. We demonstrate the advantages of M3Act across three core experiments. The results suggest our synthetic dataset can significantly improve the performance of several downstream methods and replace real-world datasets to reduce cost. Notably, M3Act improves the state-of-the-art MOTRv2 on DanceTrack dataset, leading to a hop on the leaderboard from 10th to 2nd place. Moreover, M3Act opens new research for controllable 3D group activity generation. We define multiple metrics and propose a competitive baseline for the novel task. Our code and data are available at our project page: http://cjerry1243.github.io/M3Act.