Bipartite Graph Diffusion Model for Human Interaction Generation

TL;DR

This paper introduces BiGraphDiff, a bipartite graph diffusion model that leverages transformer architecture to generate realistic human interactions, achieving state-of-the-art results on benchmark datasets.

Contribution

The paper presents a novel bipartite graph diffusion approach specifically designed for human interaction generation, integrating geometric constraints and transformer models.

Findings

Achieves new state-of-the-art results on human interaction benchmarks.

Effectively models geometric constraints between skeleton nodes.

Demonstrates superior generative quality over existing methods.

Abstract

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.