← Search

Jihua Peng

2 accepted papers

2026

Glimpse: Geometry Learning of Multi-scale Structural Priors for 3D Pose Estimation

ICML 2026poster

Monocular 3D human pose estimation is fundamentally challenged by severe occlusion and inherent depth ambiguity. To address this, we propose Glimpse, a framework that learns robust 3D poses by explicitly modeling anatomical geometry from a single image. We recast the problem as geometry learning of …

Cited by 0SourceScholar
2024

KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation

CVPR 2024poster

This paper presents a novel Kinematics and Trajectory Prior Knowledge-Enhanced Transformer (KTPFormer) which overcomes the weakness in existing transformer-based methods for 3D human pose estimation that the derivation of Q K V vectors in their self-attention mechanisms are all based on simple linea…