Geometry-Driven Self-Supervised Method for 3D Human Pose Estimation


  • Yang Li Beijing Institute of Technology
  • Kan Li Beijing Institute of Technology
  • Shuai Jiang University of Technology Sydney
  • Ziyue Zhang University of Technology Sydney
  • Congzhentao Huang University of Technology Sydney
  • Richard Yi Da Xu University of Technology Sydney



The neural network based approach for 3D human pose estimation from monocular images has attracted growing interest. However, annotating 3D poses is a labor-intensive and expensive process. In this paper, we propose a novel self-supervised approach to avoid the need of manual annotations. Different from existing weakly/self-supervised methods that require extra unpaired 3D ground-truth data to alleviate the depth ambiguity problem, our method trains the network only relying on geometric knowledge without any additional 3D pose annotations. The proposed method follows the two-stage pipeline: 2D pose estimation and 2D-to-3D pose lifting. We design the transform re-projection loss that is an effective way to explore multi-view consistency for training the 2D-to-3D lifting network. Besides, we adopt the confidences of 2D joints to integrate losses from different views to alleviate the influence of noises caused by the self-occlusion problem. Finally, we design a two-branch training architecture, which helps to preserve the scale information of re-projected 2D poses during training, resulting in accurate 3D pose predictions. We demonstrate the effectiveness of our method on two popular 3D human pose datasets, Human3.6M and MPI-INF-3DHP. The results show that our method significantly outperforms recent weakly/self-supervised approaches.




How to Cite

Li, Y., Li, K., Jiang, S., Zhang, Z., Huang, C., & Xu, R. Y. D. (2020). Geometry-Driven Self-Supervised Method for 3D Human Pose Estimation. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 11442-11449.



AAAI Technical Track: Vision