Learning a Depth Covariance Function

03/21/2023

∙

by   Eric Dexheimer, et al.

∙

0

∙

share

We propose learning a depth covariance function with applications to geometric vision tasks. Given RGB images as input, the covariance function can be flexibly used to define priors over depth functions, predictive distributions given observations, and methods for active point selection. We leverage these techniques for a selection of downstream tasks: depth completion, bundle adjustment, and monocular dense visual odometry.