Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning

arXiv:2404.05218v1 Announce Type: new
Abstract: 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 …

agent arxiv cs.ai cs.cv forecasting human long-term multi-agent trajectory type via