Do Planar Constraints Improve Camera Pose Estimation in Monocular SLAM?

Charlotte Arndt, Reza Sabzevari, Javier Civera

ICCVW 2023 pp. 2213-2222

doi:10.1109/ICCVW60793.2023.00236 /iccvw/2023/arndt2023iccvw-planar/

Abstract

Geometric structures such as lines and planes are relevant in SLAM, as they improve the map interpretability and usability for downstream tasks. Planar landmarks add structural constraints to the map optimization, which could improve the accuracy of camera pose estimates. However, does the latter really happen in practice? In this paper, we thoroughly evaluate the effect of adding planar constraints in monocular SLAM, both in simulated and real scenes. Our experiments show that, in practical use cases, the benefit of adding such planar constraint shows benefits for scene estimation but limited effect in the camera pose estimation.

ICCVW Semantic Scholar

Cite

Text

Arndt et al. "Do Planar Constraints Improve Camera Pose Estimation in Monocular SLAM?." IEEE/CVF International Conference on Computer Vision Workshops, 2023. doi:10.1109/ICCVW60793.2023.00236

Markdown

[Arndt et al. "Do Planar Constraints Improve Camera Pose Estimation in Monocular SLAM?." IEEE/CVF International Conference on Computer Vision Workshops, 2023.](https://mlanthology.org/iccvw/2023/arndt2023iccvw-planar/) doi:10.1109/ICCVW60793.2023.00236

BibTeX

@inproceedings{arndt2023iccvw-planar,
  title     = {{Do Planar Constraints Improve Camera Pose Estimation in Monocular SLAM?}},
  author    = {Arndt, Charlotte and Sabzevari, Reza and Civera, Javier},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2023},
  pages     = {2213-2222},
  doi       = {10.1109/ICCVW60793.2023.00236},
  url       = {https://mlanthology.org/iccvw/2023/arndt2023iccvw-planar/}
}