Human pose estimation is a challenging task due to its structured data sequence nature. Existing methods primarily focus on pair-wise interaction of body joints, which is insufficient for scenarios involving overlapping joints and rapidly changing poses. To overcome these issues, we introduce a novel approach, the High-order Directed Transformer (HDFormer), which leverages high-order bone and joint relationships for improved pose estimation. Specifically, HDFormer incorporates both self-attention and high-order attention to formulate a multi-order attention module. This module facilitates first-order "joint↔joint", second-order "bone↔joint", and high-order "hyperbone↔joint" interactions, effectively addressing issues in complex and occlusion-heavy situations. In addition, modern CNN techniques are integrated into the transformer-based architecture, balancing the trade-off between performance and efficiency. HDFormer significantly outperforms state-of-the-art (SOTA) models on Human3.6M and MPI-INF-3DHP datasets, requiring only 1/10 of the parameters and significantly lower computational costs. Moreover, HDFormer demonstrates broad real-world applicability, enabling real-time, accurate 3D pose estimation. The source code is in https://github.com/hyer/HDFormer
@article{arxiv.2302.01825,
title = {HDFormer: High-order Directed Transformer for 3D Human Pose Estimation},
author = {Hanyuan Chen and Jun-Yan He and Wangmeng Xiang and Zhi-Qi Cheng and Wei Liu and Hanbing Liu and Bin Luo and Yifeng Geng and Xuansong Xie},
journal= {arXiv preprint arXiv:2302.01825},
year = {2023}
}
Comments
Accepted to IJCAI 2023; 9 pages, 5 figures, 7 tables; the code is at https://github.com/hyer/HDFormer