Learning a Depth Covariance Function

03/21/2023
by   Eric Dexheimer, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset