Diverse Yet Consistent: Context-Guided Diffusion with Energy-Based Joint Refinement for Multi-Agent Motion Prediction

TL;DR

This paper introduces a diffusion-based framework that leverages contextual information and energy-based refinement to improve multi-agent motion prediction, achieving state-of-the-art results on benchmark datasets.

Contribution

The authors propose a novel diffusion model with energy-based joint refinement that enhances diversity, consistency, and accuracy in multi-agent motion prediction.

Findings

Outperforms existing methods on four benchmark datasets.

Significantly improves both marginal and joint prediction metrics.

Maintains competitive joint performance while boosting marginal accuracy.

Abstract

Deepgenerative models havebecomeapromisingapproach for human motion prediction due to their ability to capture multimodal distributions and represent diverse human be haviors. However, generating predictions that are both di verse and jointly consistent among interacting agents re mains challenging. In addition, most existing approaches are primarily evaluated using single-agent (marginal) met rics, which fail to fully reflect the joint dynamics of multi agent interactions. We propose a diffusion-based frame work that improves multi-agent motion prediction by lever aging rich contextual information from historical trajecto ries. This information is incorporated through a guidance mechanism to enhance the diversity and expressiveness of predicted motions. To further enforce interaction consis tency, we introduce an energy-based formulation that re fines the joint trajectory distribution while preserving the plausibility of individual trajectories. Extensive experi ments on four benchmark datasets demonstrate that our approach consistently outperforms existing methods. No tably, our approach substantially improves both marginal (ADE/FDE) and joint (JADE/JFDE) metrics on ETH/UCY over strong marginal baselines. Compared with prior joint prediction methods, it delivers significant gains in marginal metrics while maintaining competitive joint performance.