Timezone: »

Multi-Person 3D Motion Prediction with Multi-Range Transformers
Jiashun Wang · Huazhe Xu · Medhini Narasimhan · Xiaolong Wang

Tue Dec 07 04:30 PM -- 06:00 PM (PST) @ Virtual #None

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/.

Author Information

Jiashun Wang (University of California, San Diego)
Huazhe Xu (UC Berkeley)
Medhini Narasimhan (UC Berkeley)

CS Graduate student at the University of Illinois Urbana Champaign pursuing Computer Vision and Deep Learning research.

Xiaolong Wang (UC San Diego)

More from the Same Authors