Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction
This work addresses the problem of accurate human motion forecasting for applications like robotics and animation, presenting an incremental improvement over existing methods.
The authors tackled 3D skeleton-based human motion prediction by proposing a dynamic multiscale graph neural network (DMGNN) that adaptively models body relations, achieving state-of-the-art performance on Human 3.6M and CMU Mocap datasets for both short and long-term predictions.
We propose novel dynamic multiscale graph neural networks (DMGNN) to predict 3D skeleton-based human motions. The core idea of DMGNN is to use a multiscale graph to comprehensively model the internal relations of a human body for motion feature learning. This multiscale graph is adaptive during training and dynamic across network layers. Based on this graph, we propose a multiscale graph computational unit (MGCU) to extract features at individual scales and fuse features across scales. The entire model is action-category-agnostic and follows an encoder-decoder framework. The encoder consists of a sequence of MGCUs to learn motion features. The decoder uses a proposed graph-based gate recurrent unit to generate future poses. Extensive experiments show that the proposed DMGNN outperforms state-of-the-art methods in both short and long-term predictions on the datasets of Human 3.6M and CMU Mocap. We further investigate the learned multiscale graphs for the interpretability. The codes could be downloaded from https://github.com/limaosen0/DMGNN.