Multi-Person 3D Motion Prediction with Multi-Range Transformers

TL;DR

This paper introduces a Multi-Range Transformers framework for multi-person 3D motion prediction, capturing individual actions and social interactions, and can predict multiple persons' motions simultaneously with high accuracy.

Contribution

The novel Multi-Range Transformers model effectively integrates local and global social cues for multi-person 3D motion prediction, enabling simultaneous prediction of many individuals.

Findings

Outperforms state-of-the-art long-term 3D motion prediction methods.

Generates diverse social interaction scenarios.

Predicts motions for up to 15 persons simultaneously.

Abstract

We propose a novel framework for multi-person 3D motion trajectory prediction. Our key observation is that a human's action and behaviors may highly depend on the other persons around. Thus, instead of predicting each human pose trajectory in isolation, we introduce a Multi-Range Transformers model which contains of a local-range encoder for individual motion and a global-range encoder for social interactions. The Transformer decoder then performs prediction for each person by taking a corresponding pose as a query which attends to both local and global-range encoder features. Our model not only outperforms state-of-the-art methods on long-term 3D motion prediction, but also generates diverse social interactions. More interestingly, our model can even predict 15-person motion simultaneously by automatically dividing the persons into different interaction groups. Project page with code is available at https://jiashunwang.github.io/MRT/.