Learning a Depth Covariance Function

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dexheimer, Eric, Davison, Andrew J.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917618655428608
author Dexheimer, Eric
Davison, Andrew J.
author_facet Dexheimer, Eric
Davison, Andrew J.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2303_12157
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Learning a Depth Covariance Function
Dexheimer, Eric
Davison, Andrew J.
Computer Vision and Pattern Recognition
Machine Learning
Robotics
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.
title Learning a Depth Covariance Function
topic Computer Vision and Pattern Recognition
Machine Learning
Robotics
url https://arxiv.org/abs/2303.12157