Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Prediction
This work addresses a key bottleneck in graph-based motion prediction for applications like robotics and animation, though it is incremental as it builds on existing GCN methods.
The paper tackles the problem of constructing graphs and performing message passing for skeleton-based human motion prediction by proposing a Dynamic Dense Graph Convolutional Network (DD-GCN), which achieves state-of-the-art performance on benchmark datasets like Human 3.6M and CMU Mocap, especially in long-term protocols.
Graph Convolutional Networks (GCN) which typically follows a neural message passing framework to model dependencies among skeletal joints has achieved high success in skeleton-based human motion prediction task. Nevertheless, how to construct a graph from a skeleton sequence and how to perform message passing on the graph are still open problems, which severely affect the performance of GCN. To solve both problems, this paper presents a Dynamic Dense Graph Convolutional Network (DD-GCN), which constructs a dense graph and implements an integrated dynamic message passing. More specifically, we construct a dense graph with 4D adjacency modeling as a comprehensive representation of motion sequence at different levels of abstraction. Based on the dense graph, we propose a dynamic message passing framework that learns dynamically from data to generate distinctive messages reflecting sample-specific relevance among nodes in the graph. Extensive experiments on benchmark Human 3.6M and CMU Mocap datasets verify the effectiveness of our DD-GCN which obviously outperforms state-of-the-art GCN-based methods, especially when using long-term and our proposed extremely long-term protocol.