Skip to main content

HTNET: HUMAN TOPOLOGY AWARE NETWORK FOR 3D HUMAN POSE ESTIMATION

Jialun Cai (Peking university); Hong Liu (Peking University Shenzhen Graduate School); Runwei Ding (Peking University Shenzhen Graduate School); Wenhao Li (Peking University); Jianbing Wu (Peking University); Miaoju Ban (Peking University )

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
06 Jun 2023

3D human pose estimation errors would propagate along the human body topology and accumulate at the end joints of limbs. Inspired by the backtracking mechanism in automatic control systems, we design an Intra-Part Constraint module that utilizes the parent nodes as the reference to build topological constraints for end joints at the part level. Further considering the hierarchy of the human topology, joint-level and body-level dependencies are captured via graph convolutional networks and self-attentions, respectively. Based on these designs, we propose a novel Human Topology aware Network (HTNet), which adopts a channel-split progressive strategy to sequentially learn the structural priors of the human topology from multiple semantic levels: joint, part, and body. Extensive experiments show that the proposed method improves the estimation accuracy by 18.7% on the end joints of limbs and achieves state-of-the-art results on Human3.6M and MPI-INF-3DHP datasets. The code will be open-sourced.

More Like This

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00