Learning Temporal 3D Human Pose Estimation with Pseudo-Labels
Bouazizi A, Kressel U, Belagiannis V (2021)
Publication Type: Conference contribution
Publication year: 2021
Publisher: Institute of Electrical and Electronics Engineers Inc.
Conference Proceedings Title: AVSS 2021 - 17th IEEE International Conference on Advanced Video and Signal-Based Surveillance
Event location: Virtual, Online, USA
ISBN: 9781665433969
DOI: 10.1109/AVSS52988.2021.9663755
Abstract
We present a simple, yet effective, approach for self-supervised 3D human pose estimation. Unlike the prior work, we explore the temporal information next to the multi-view self-supervision. During training, we rely on triangulating 2D body pose estimates of a multiple-view camera system. A temporal convolutional neural network is trained with the generated 3D ground-truth and the geometric multi-view consistency loss, imposing geometrical constraints on the predicted 3D body skeleton. During inference, our model receives a sequence of 2D body pose estimates from a single-view to predict the 3D body pose for each of them. An extensive evaluation shows that our method achieves state-of-the-art performance in the Human3.6M and MPI-INF-3DHP benchmarks. Our code and models are publicly available at https://github.com/vru2020/TM_HPE/.
Authors with CRIS profile
Involved external institutions
Germany (DE)How to cite
APA:
Bouazizi, A., Kressel, U., & Belagiannis, V. (2021). Learning Temporal 3D Human Pose Estimation with Pseudo-Labels. In AVSS 2021 - 17th IEEE International Conference on Advanced Video and Signal-Based Surveillance. Virtual, Online, USA: Institute of Electrical and Electronics Engineers Inc..
MLA:
Bouazizi, Arij, Ulrich Kressel, and Vasileios Belagiannis. "Learning Temporal 3D Human Pose Estimation with Pseudo-Labels." Proceedings of the 17th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2021, Virtual, Online, USA Institute of Electrical and Electronics Engineers Inc., 2021.
BibTeX: Download