Gaussian-Mixture Latent Flow for Stochastic 3D Human Motion Prediction

2026-08-21

AI Summary

该研究针对随机3D人体运动预测中的合理性与不确定性量化问题，提出了一种基于潜流模型的方法，并使用数据驱动的高斯混合先验，提高了预测的准确性和合理性。

Abstract

Stochastic human motion prediction aims to forecast future motion distributions. Although recent studies have achieved strong performance in terms of accuracy and diversity, they often overlook plausibility (e.g., resulting in physically unrealistic predictions) and uncertainty quantification, both of which are essential for real-world applications and downstream tasks. To address these issues, we propose a latent flow-based model equipped with a data-driven Gaussian mixture prior that more effectively disentangles diverse human behaviors than conventional single-modal priors. This prior is derived from patterns in the training data without requiring additional annotations. Furthermore, the fully invertible nature of our model enables natural uncertainty quantification through tractable likelihood computation. Experiments on the Human3.6M and AMASS datasets demonstrate that our approach achieves state-of-the-art performance in both accuracy and plausibility.

Problem

• stochastic human motion prediction
• plausibility
• uncertainty quantification

Innovation

• Gaussian Mixture Prior
• Latent Flow
• Uncertainty Quantification
• Stochastic Human Motion Prediction