English

Geo-Supervised Visual Depth Prediction

Computer Vision and Pattern Recognition 2019-06-13 v4 Robotics

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.

Keywords

Cite

@article{arxiv.1807.11130,
  title  = {Geo-Supervised Visual Depth Prediction},
  author = {Xiaohan Fei and Alex Wong and Stefano Soatto},
  journal= {arXiv preprint arXiv:1807.11130},
  year   = {2019}
}

Comments

ICRA 2019, RA-L 2019

R2 v1 2026-06-23T03:18:24.910Z