Humans naturally interact with both others and the surrounding multiple objects, engaging in various social activities. However, recent advances in modeling human-object interactions mostly focus on perceiving isolated individuals and objects, due to fundamental data scarcity. In this paper, we introduce HOI-M3, a novel large-scale dataset for modeling the interactions of Multiple huMans and Multiple objects. Notably, it provides accurate 3D tracking for both humans and objects from dense RGB and object-mounted IMU inputs, covering 199 sequences and 181M frames of diverse humans and objects under rich activities. With the unique HOI-M3 dataset, we introduce two novel data-driven tasks with companion strong baselines: monocular capture and unstructured generation of multiple human-object interactions. Extensive experiments demonstrate that our dataset is challenging and worthy of further research about multiple human-object interactions and behavior analysis. Our HOI-M3 dataset, corresponding codes, and pre-trained models will be disseminated to the community for future research.
@article{arxiv.2404.00299,
title = {HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environment},
author = {Juze Zhang and Jingyan Zhang and Zining Song and Zhanhe Shi and Chengfeng Zhao and Ye Shi and Jingyi Yu and Lan Xu and Jingya Wang},
journal= {arXiv preprint arXiv:2404.00299},
year = {2024}
}