article · 2023

Learning a Depth Covariance Function

Cited by 17Abstract and details only

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.

Cite this paper

APA 7

Dexheimer, E., & Davison, A. J. (2023). Learning a Depth Covariance Function. https://doi.org/10.1109/cvpr52729.2023.01261

MLA 9

Dexheimer, Eric, and Andrew J. Davison. “Learning a Depth Covariance Function.” 2023, pp. 13122–31, https://doi.org/10.1109/cvpr52729.2023.01261.

Chicago

Dexheimer, Eric, and Andrew J. Davison. 2023. “Learning a Depth Covariance Function.” https://doi.org/10.1109/cvpr52729.2023.01261.

Harvard

Dexheimer, E. and Davison, A.J. (2023) ‘Learning a Depth Covariance Function’. Available at: https://doi.org/10.1109/cvpr52729.2023.01261.

BibTeX

@article{dexheimer2023learning,
  title = {{Learning a Depth Covariance Function}},
  author = {Dexheimer, Eric and Davison, Andrew J.},
  pages = {13122--13131},
  year = {2023},
  doi = {10.1109/cvpr52729.2023.01261}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.