Semi-Dynamic Hypergraph Neural Network for 3D Pose Estimation

Semi-Dynamic Hypergraph Neural Network for 3D Pose Estimation

Shengyuan Liu, Pei Lv, Yuzhen Zhang, Jie Fu, Junjin Cheng, Wanqing Li, Bing Zhou, Mingliang Xu

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
Main track. Pages 782-788. https://doi.org/10.24963/ijcai.2020/109

This paper proposes a novel Semi-Dynamic Hypergraph Neural Network (SD-HNN) to estimate 3D human pose from a single image. SD-HNN adopts hypergraph to represent the human body to effectively exploit the kinematic constrains among adjacent and non-adjacent joints. Specifically, a pose hypergraph in SD-HNN has two components. One is a static hypergraph constructed according to the conventional tree body structure. The other is the semi-dynamic hypergraph representing the dynamic kinematic constrains among different joints. These two hypergraphs are combined together to be trained in an end-to-end fashion. Unlike traditional Graph Convolutional Networks (GCNs) that are based on a fixed tree structure, the SD-HNN can deal with ambiguity in human pose estimation. Experimental results demonstrate that the proposed method achieves state-of-the-art performance both on the Human3.6M and MPI-INF-3DHP datasets.
Keywords:
Computer Vision: Biometrics, Face and Gesture Recognition
Machine Learning: Deep Learning: Convolutional networks
Computer Vision: 2D and 3D Computer Vision