Absolute 3D Human Pose Estimation via Weakly-supervised Learning

Yiru Guo, Zerui Chen

Abstract: In this paper, we attempt to estimate absolute 3D human poses directly from monocular images. Not limited to estimating root-relative 3D human poses, our method can recover the absolute depth for each joint. Our method is trained with multi-view images in a weakly-supervised manner removing the need for 3D ground-truth annotations. We conduct extensive experiments on the Human3.6M benchmark to show the effectiveness of our method.