Learning Temporal 3D Human Pose Estimation with Pseudo-Labels
This work improves 3D human pose estimation for computer vision applications, but it is incremental as it builds on existing multi-view and temporal methods.
The paper tackles 3D human pose estimation by using temporal information and multi-view self-supervision with pseudo-labels, achieving state-of-the-art results on Human3.6M and MPI-INF-3DHP benchmarks.
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 \url{https://github.com/vru2020/TM_HPE/}.