May 28, 2022 · We propose a hierarchical poselet-guided graph convolutional network (HPGCN) for 3D pose estimation from 2D poses.

... hierarchical poselet-guided graph convolutional network (HPGCN) for 3D pose estimation from 2D poses. HPGCN sets five primitives of human body as basic poselets ...

We verify the effectiveness of HPGCN on three public 3D human pose benchmarks. Experimental results show that HPGCN outperforms several state-of-the-art methods ...

Oct 22, 2024 · HPGCN sets five primitives of human body as basic poselets, and constitutes high-level poselets according to the kinematic configuration of ...

HPGCN: Hierarchical poselet-guided graph convolutional network for 3D pose estimation. Authors: Yongpeng Wu 0002, Dehui Kong, Shaofan Wang, Jinghua Li ...

Missing: HPGCN: poselet-

Yongpeng Wu's 5 research works with 35 citations, including: Joint multi-scale transformers and pose equivalence constraints for 3D human pose estimation.

This paper proposes a one-stage GCN approach for 3D object detection and poses estimation by structuring non-linearly distributed points of a graph.

3D pose estimation remains a challenging task since human poses exhibit high ambiguity and multi-granularity. Traditional graph convolution networks (GCNs) ...

Graph convolutional network (GCN) is a widespread architecture for 2D-to-3D human pose estimation (HPE). Vanilla graph convolution is the key in GCN for ...