Adaptive Hypergraph-Based 3D Multi-Person Pose Estimation Method for Intangible Cultural Heritage Dance Videos
Xingquan Cai, Xiaoyu Wang, Kaijie Qu, Mengrui Dai, Ying Li · 2025
Despite recent advancements, 3D multi-person pose estimation from monocular videos remains challenging due to common issues such as occlusions caused by clothing and limbs, as well as inaccuracies in person detection. Current 3D multi-person pose estimation methods typically treat individuals as independent entities for estimation. This methodology has significant limitations, particularly in its failure to fully account for the rich interactive information between individuals and within limbs. To address these challenges, we propose a novel method for monocular 3D multi-person pose estimation. Firstly, it constructs Intra-Hypergraph and Inter-Hypergraph to represent inter-limb and inter-individual interaction information. Subsequently, we design adaptive hypergraph convolutional networks to extract spatial features from 2D human pose sequences. Finally, after the temporal attention module outputs the coordinates of the predicted 3D joint points. Quantitative and qualitative evaluations demonstrate the effectiveness of the proposed method.