Publication
Uncertainty-Aware Camera Pose Estimation from Points and Lines
Conference Article
Conference
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Edition
2021
Pages
4657-4666
Doc link
https://doi.org/10.1109/CVPR46437.2021.00463
File
Authors
-
Vakhitov, Alexander
-
Ferraz Colomina, Luis
-
Agudo Martínez, Antonio
-
Moreno Noguer, Francesc
Projects associated
Abstract
Perspective-n-Point-and-Line (PnPL) algorithms aim at fast, accurate, and robust camera localization with respect to a 3D model from 2D-3D feature correspondences, being a major part of modern robotic and AR/VR systems. Current point-based pose estimation methods use only 2D feature detection uncertainties, and the line-based methods do not take uncertainties into account. In our setup, both 3D coordinates and 2D projections of the features are considered uncertain. We propose PnP(L) solvers based on EPnP and DLS for the uncertainty-aware pose estimation. We also modify motion-only bundle adjustment to take 3D uncertainties into account. We perform exhaustive synthetic and real experiments on two different visual odometry datasets. The new PnP(L) methods outperform the state-of-the-art on real data in isolation, showing an increase in mean translation accuracy by 18% on a representative subset of KITTI, while the new uncertain refinement improves pose accuracy for most of the solvers, e.g. decreasing mean translation error for the EPnP by 16% compared to the standard refinement on the same dataset.
Categories
computer vision.
Scientific reference
A. Vakhitov, L. Ferraz, A. Agudo and F. Moreno-Noguer. Uncertainty-Aware Camera Pose Estimation from Points and Lines, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, Nashville, TN, USA (Virtual), pp. 4657-4666, Computer Vision Foundation.
Follow us!