Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction

by   Maosen Li, et al.
HUAWEI Technologies Co., Ltd.

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.


page 1

page 2

page 3

page 4


Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction

We propose a multiscale spatio-temporal graph neural network (MST-GNN) t...

An Attractor-Guided Neural Networks for Skeleton-Based Human Motion Prediction

Joint relation modeling is a curial component in human motion prediction...

Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Prediction

3D skeleton-based action recognition and motion prediction are two essen...

Multiscale Residual Learning of Graph Convolutional Sequence Chunks for Human Motion Prediction

A new method is proposed for human motion prediction by learning tempora...

Image Classification using Graph Neural Network and Multiscale Wavelet Superpixels

Prior studies using graph neural networks (GNNs) for image classificatio...

Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction

Graph convolutional network based methods that model the body-joints' re...

Graph Cross Networks with Vertex Infomax Pooling

We propose a novel graph cross network (GXN) to achieve comprehensive fe...

Please sign up or login with your details

Forgot password? Click here to reset