Learning Multiscale Correlations for Human Motion Prediction

TL;DR

This paper introduces a multiscale graph convolution network that effectively captures correlations among human body components to improve the accuracy of human motion prediction, especially for complex, aperiodic motions.

Contribution

It proposes a novel multiscale graph convolution network with an adaptive encoding module and a coarse-to-fine decoding strategy for better motion prediction.

Findings

Achieves state-of-the-art results on Human3.6M and CMU datasets.

Excels in predicting complex and aperiodic human motions.

Outperforms existing methods in both short-term and long-term predictions.

Abstract

In spite of the great progress in human motion prediction, it is still a challenging task to predict those aperiodic and complicated motions. We believe that to capture the correlations among human body components is the key to understand the human motion. In this paper, we propose a novel multiscale graph convolution network (MGCN) to address this problem. Firstly, we design an adaptive multiscale interactional encoding module (MIEM) which is composed of two sub modules: scale transformation module and scale interaction module to learn the human body correlations. Secondly, we apply a coarse-to-fine decoding strategy to decode the motions sequentially. We evaluate our approach on two standard benchmark datasets for human motion prediction: Human3.6M and CMU motion capture dataset. The experiments show that the proposed approach achieves the state-of-the-art performance for both short-term and long-term prediction especially in those complicated action category.