ML Anthology

Information-Driven Direct RGB-D Odometry

Alejandro Fontan, Javier Civera, Rudolph Triebel
CVPR 2020
doi:10.1109/CVPR42600.2020.00498 /cvpr/2020/fontan2020cvpr-informationdriven/

Abstract

This paper presents an information-theoretic approach to point selection in direct RGB-D odometry. The aim is to select only the most informative measurements, in order to reduce the optimization problem with a minimal impact in the accuracy. It is usual practice in visual odometry/SLAM to track several hundreds of points, achieving real-time performance in high-end desktop PCs. Reducing their computational footprint will facilitate the implementation of odometry and SLAM in low-end platforms such as small robots and AR/VR glasses. Our experimental results show that our novel information-based selection criterion allows us to reduce the number of tracked points an order of magnitude (down to only 24 of them), achieving an accuracy similar to the state of the art (sometimes outperforming it) while reducing 10 times the computational demand.

PDF CVPR Semantic Scholar

Cite

Text

Fontan et al. "Information-Driven Direct RGB-D Odometry." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. doi:10.1109/CVPR42600.2020.00498

Markdown

[Fontan et al. "Information-Driven Direct RGB-D Odometry." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.](https://mlanthology.org/cvpr/2020/fontan2020cvpr-informationdriven/) doi:10.1109/CVPR42600.2020.00498

BibTeX

@inproceedings{fontan2020cvpr-informationdriven,
  title     = {{Information-Driven Direct RGB-D Odometry}},
  author    = {Fontan, Alejandro and Civera, Javier and Triebel, Rudolph},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2020},
  doi       = {10.1109/CVPR42600.2020.00498},
  url       = {https://mlanthology.org/cvpr/2020/fontan2020cvpr-informationdriven/}
}