Learning a Depth Covariance Function

Eric Dexheimer, Andrew J. Davison; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 13122-13131

Abstract

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.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dexheimer_2023_CVPR, author = {Dexheimer, Eric and Davison, Andrew J.}, title = {Learning a Depth Covariance Function}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13122-13131} }