Bias-Eliminated PnP for Stereo Visual Odometry: Provably Consistent and Large-Scale Localization
Bias-Eliminated PnP for Stereo Visual Odometry: Provably Consistent and Large-Scale Localization
This paper introduces a bias-eliminated weighted perspective-n-point (PnP) estimator designed for stereo visual odometry, offering provable consistency and improved performance in large-scale environments.
The authors present a theoretically grounded estimator that addresses bias in stereo visual odometry, validated on established benchmarks including KITTI and Oxford RobotCar.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
t enhances the suppression of pose estimation errors. We validate the performance of our method on the KITTI and Oxford RobotCar datasets. Experimental results demonstrate that our method: 1) achieves significant improvements in both relative pose error and absolute trajectory error in large-scale environments; 2) provides reliable localization under erratic and unpredictable robot motions. The successful implementat
Open source S4
ion of the Bias-Eli-W PnP in stereo VO indicates the importance of information screening in robotic estimation tasks with high-uncertainty measurements, shedding light on diverse applications where PnP is a key ingredient.
Open source S5
Bias-Eliminated PnP for Stereo Visual Odometry: Provably Consistent and Large-Scale Localization
Open source S1
arXiv:2504.17410v2 Announce Type: replace Abstract: In this paper, we first present a bias-eliminated weighted (Bias-Eli-W) perspective-n-point (PnP) estimator for stereo visual odometry (VO) with provable consistency. Specifically, leveraging statistical theory, we develop an asymptotically unbiased and $\sqrt {n}$-consistent PnP estimator that accounts for varying 3D triangulation uncertainties, ensuring that the r
Open source S2
elative pose estimate converges to the ground truth as the number of features increases. Next, on the stereo VO pipeline side, we propose a framework that continuously triangulates contemporary features for tracking new frames, effectively decoupling temporal dependencies between pose and 3D point errors. We integrate the Bias-Eli-W PnP estimator into the proposed stereo VO pipeline, creating a synergistic effect tha
Open source S3
Source：arXiv Robotics — research abstracts · arxiv.org