HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environment
This addresses the need for better datasets in human-object interaction research, particularly for social activities involving multiple entities, though it is incremental as it builds on existing work by expanding data availability.
The paper tackles the problem of modeling interactions between multiple humans and objects, which is limited by data scarcity, by introducing HOI-M3, a large-scale dataset with 199 sequences and 181M frames providing accurate 3D tracking from RGB and IMU inputs, enabling tasks like monocular capture and generation of such interactions.
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.