Multi-Person 3D Motion Prediction with Multi-Range Transformers
This addresses the problem of predicting realistic social interactions in multi-person scenarios for applications like robotics and animation, representing a novel method for a known bottleneck.
The paper tackles multi-person 3D motion trajectory prediction by introducing a Multi-Range Transformers model that encodes individual motion and social interactions, outperforming state-of-the-art methods on long-term prediction and enabling simultaneous prediction for up to 15 persons.
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/.