<ul><li>Existing 2D-to-3D human pose estimation methods struggle with occlusion issue due to limited input representation.</li><li>Hierarchical Pose AutoRegressive Transformer (HiPART) is proposed to address the occlusion issue in 2D-to-3D lifting.</li><li>HiPART generates hierarchical 2D dense poses from sparse 2D pose using a two-stage generative densification method.</li><li>HiPART achieves state-of-the-art performance on single-frame-based 3D human pose estimation by improving robustness in occluded scenarios.</li></ul>

HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimation

Discover more