Skip to main content
placeholder image

Semi-dynamic hypergraph neural network for 3D pose estimation

Conference Paper


Abstract


  • 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.

Publication Date


  • 2020

Citation


  • Liu, S., Lv, P., Zhang, Y., Fu, J., Cheng, J., Li, W., . . . Xu, M. (2020). Semi-dynamic hypergraph neural network for 3D pose estimation. In IJCAI International Joint Conference on Artificial Intelligence Vol. 2021-January (pp. 782-788).

Scopus Eid


  • 2-s2.0-85097355032

Web Of Science Accession Number


Start Page


  • 782

End Page


  • 788

Volume


  • 2021-January

Abstract


  • 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.

Publication Date


  • 2020

Citation


  • Liu, S., Lv, P., Zhang, Y., Fu, J., Cheng, J., Li, W., . . . Xu, M. (2020). Semi-dynamic hypergraph neural network for 3D pose estimation. In IJCAI International Joint Conference on Artificial Intelligence Vol. 2021-January (pp. 782-788).

Scopus Eid


  • 2-s2.0-85097355032

Web Of Science Accession Number


Start Page


  • 782

End Page


  • 788

Volume


  • 2021-January