Abstract
We present a novel data-driven regularizer for weakly-supervised learning of 3D
human pose estimation that eliminates the drift problem that affects existing approaches.
We do this by moving the stereo reconstruction problem into the loss of the network
itself. This avoids the need to reconstruct 3D data prior to training and unlike previous
semi-supervised approaches, avoids the need for a warm-up period of supervised training.
The conceptual and implementational simplicity of our approach is fundamental to its
appeal. Not only is it straightforward to augment many weakly-supervised approaches
with our additional re-projection based loss, but it is obvious how it shapes reconstructions
and prevents drift. As such we believe it will be a valuable tool for any researcher working
in weakly-supervised 3D reconstruction. Evaluating on Panoptic, the largest multi-camera
and markerless dataset available, we obtain an accuracy that is essentially indistinguishable
from a strongly-supervised approach making full use of 3D groundtruth in training.