Uncertainty-Aware Camera Pose Estimation from Points and Lines

TL;DR

This paper introduces uncertainty-aware PnP(L) algorithms that incorporate both 2D and 3D feature uncertainties for improved camera pose estimation in robotics and AR/VR applications.

Contribution

It proposes novel PnP(L) solvers based on EPnP and DLS that account for feature uncertainties, enhancing accuracy over existing methods.

Findings

Outperforms state-of-the-art in real data pose accuracy

Increases mean translation accuracy by 18% on KITTI dataset

Reduces mean translation error by 16% with the new refinement

Abstract

Perspective-n-Point-and-Line (P$n$PL) 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. The code is available at https://alexandervakhitov.github.io/uncertain-pnp/.