论文标题
基于3D骨架的人类运动预测的动态多尺度图神经网络
Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction
论文作者
论文摘要
我们提出了新型的动态多尺度图神经网络（DMGNN），以预测基于3D骨架的人类运动。 DMGNN的核心思想是使用多尺度图来全面地对人体的内部关系进行运动特征学习。该多尺度图在训练过程中具有自适应，并且在跨网络层的跨训练和动态上是自适应的。基于此图，我们提出了一个多尺度图计算单元（MGCU），以在各个尺度上提取单个尺度和保险丝特征。整个模型是Action类别-Nostic，并遵循编码器框架。编码器由一系列MGCU组成，以学习运动功能。解码器使用提出的基于图的门复发单元来生成未来的姿势。广泛的实验表明，在人类36M和CMU MOCAP的数据集上，所提出的DMGNN在短期和长期预测中均优于最先进的方法。我们进一步研究了学到的多尺度图，以解释性。这些代码可以从https://github.com/limaosen0/dmgnn下载。
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.
