Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning
This addresses the challenge of predicting human motion over long timescales with multiple agents, which is important for applications like robotics and surveillance, though it appears incremental as it builds on existing forecasting methods.
The paper tackles the problem of long-term multi-agent 3D human pose forecasting by proposing a model that uses a coarse-to-fine approach with interaction-aware trajectory conditioning, improving performance in complex environments and achieving state-of-the-art results on both complex and simpler datasets.
Human pose forecasting garners attention for its diverse applications. However, challenges in modeling the multi-modal nature of human motion and intricate interactions among agents persist, particularly with longer timescales and more agents. In this paper, we propose an interaction-aware trajectory-conditioned long-term multi-agent human pose forecasting model, utilizing a coarse-to-fine prediction approach: multi-modal global trajectories are initially forecasted, followed by respective local pose forecasts conditioned on each mode. In doing so, our Trajectory2Pose model introduces a graph-based agent-wise interaction module for a reciprocal forecast of local motion-conditioned global trajectory and trajectory-conditioned local pose. Our model effectively handles the multi-modality of human motion and the complexity of long-term multi-agent interactions, improving performance in complex environments. Furthermore, we address the lack of long-term (6s+) multi-agent (5+) datasets by constructing a new dataset from real-world images and 2D annotations, enabling a comprehensive evaluation of our proposed model. State-of-the-art prediction performance on both complex and simpler datasets confirms the generalized effectiveness of our method. The code is available at https://github.com/Jaewoo97/T2P.