CVLGMar 30, 2025

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

arXiv:2503.23331v113 citationsh-index: 27CVPR
Originality Incremental advance
AI Analysis

This addresses occlusion issues in 3D human pose estimation for applications like motion capture and robotics, representing an incremental improvement over existing methods.

The paper tackles the problem of 3D human pose estimation under occlusion by generating hierarchical 2D dense poses from sparse inputs, achieving state-of-the-art performance on single-frame-based methods and outperforming many multi-frame approaches with reduced complexity.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes