We present a simple, yet effective, approach for self-supervised 3D humanpose estimation . During training, we rely ontriangulating 2D body pose estimates of a multiple-view camera system . Atemporal convolutional neural network is trained with the generated 3Dground-truth and the geometric multi-view consistency loss, imposinggeometrical constraints on the predicted 3D body skeleton . An extensive evaluation shows thatour method achieves state-of-the-art performance in the Human3.6M andMPI-INF-3DHP benchmarks .

Author(s) : Arij Bouazizi, Ulrich Kressel, Vasileios Belagiannis

Links : PDF - Abstract

Code :
Coursera

Keywords : d - human - view - estimation - body -

Leave a Reply

Your email address will not be published. Required fields are marked *