2025/03/30 by Hongwei Zheng, Han Li, Zheng, Hongwei +11 · 3 citations
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Motion and Animation #Human Pose and Action Recognition #Machine Learning (cs.LG) #Robot Manipulation and Learning
paper · pdf · doi:10.48550/arxiv.2503.23331
openalex publication_date 2025/03/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Existing 2D-to-3D human pose estimation (HPE) methods struggle with the occlusion issue by enriching information like temporal and visual cues in the lifting stage. In this paper, we argue that these methods ignore the limitation of the sparse skeleton 2D input representation, which fundamentally restricts the 2D-to-3D lifting and worsens the occlusion issue. To address these, we propose a novel two-stage generative densification method, named Hierarchical Pose AutoRegressive Transformer (HiPART), to generate hierarchical 2D dense poses from the original sparse 2D pose. Specifically, we first develop a multi-scale skeleton tokenization module to quantize the highly dense 2D pose into hierarchical tokens and propose a Skeleton-aware Alignment to strengthen token connections. We then develop a Hierarchical AutoRegressive Modeling scheme for hierarchical 2D pose generation. With generated hierarchical poses as inputs for 2D-to-3D lifting, the proposed method shows strong robustness in occluded scenarios and achieves state-of-the-art performance on the single-frame-based 3D HPE. Moreover, it outperforms numerous multi-frame methods while reducing parameter and computational complexity and can also complement them to further enhance performance and robustness.