Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks

Despite great progress in 3D pose estimation from single-view images or videos, it remains a challenging task due to the substantial depth ambiguity and severe self-occlusions. Motivated by the effectiveness of incorporating spatial dependencies and temporal consistencies to alleviate these issues, we propose a novel graph-based method to tackle the problem of 3D human body and 3D hand pose estimation from a short sequence of 2D joint detections. Particularly, domain knowledge about the human hand (body) configurations is explicitly incorporated into the graph convolutional operations to meet the specific demand of the 3D pose estimation. Furthermore, we introduce a local-to-global network architecture, which…

• NR
  National Research Foundation
• NT
  Nanyang Technological University
• MO
  Ministry of Education, India
• UA
  University at Buffalo