Geo-Supervised Visual Depth Prediction

Xiaohan Fei, Alex Wong, Stefano Soatto

Abstract:

We propose using global orientation from inertial
measurements, and the bias it induces on the shape of objects
populating the scene, to inform visual 3D reconstruction. We
test the effect of using the resulting prior in depth prediction
from a single image, where the normal vectors to surfaces
of objects of certain classes tend to align with gravity or be
orthogonal to it. Adding such a prior to baseline methods
for monocular depth prediction yields improvements beyond
the state-of-the-art and illustrates the power of gravity as a
supervisory signal.