Bipartite Graph Diffusion Model for Human Interaction Generation

Baptiste Chopin (1) , Hao Tang (2) , Mohamed Daoudi (3, 4)

1 STARS - Spatio-Temporal Activity Recognition Systems
2 CMU - Carnegie Mellon University [Pittsburgh]
3 CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
4 IMT Nord Europe - Ecole nationale supérieure Mines-Télécom Lille Douai

The generation of natural human motion interactions is a hot topic in computer vision and computer animation. It is a challenging task due to the diversity of possible human motion interactions. Diffusion models, which have already shown remarkable generative capabilities in other domains, are a good candidate for this task. In this paper, we introduce a novel bipartite graph diffusion method (BiGraphDiff) to generate human motion interactions between two persons. Specifically, bipartite node sets are constructed to model the inherent geometric constraints between skeleton nodes during interactions. The interaction graph diffusion model is transformer-based, combining some state-of-theart motion methods. We show that the proposed achieves new state-of-the-art results on leading benchmarks for the human interaction generation task. Code, pre-trained models and additional results are available at https:// github.com/CRISTAL-3DSAM/BiGraphDiff.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Baptiste Chopin, Hao Tang, Mohamed Daoudi. Bipartite Graph Diffusion Model for Human Interaction Generation: The generation of natural human motion interactions is a hot topic in computer vision and computer animation. It is a challenging task due to the diversity of possible human motion interactions. Diffusion models, which have already shown remarkable generative capabilities in other domains, are a good candidate for this task. In this paper, we introduce a novel bipartite graph diffusion method (BiGraphDiff) to generate human motion interactions between two persons. Specifically, bipartite node sets are constructed to model the inherent geometric constraints between skeleton nodes during interactions. The interaction graph diffusion model is transformer-based, combining some state-of-the-art motion methods. We show that the proposed achieves new state-of-the-art results on leading benchmarks for the human interaction generation task. WACV 2024 - IEEE/CVF Winter Conference on Applications of Computer Vision, Jan 2024, WAIKOLOA (Hawaii), United States. ⟨hal-04274209⟩