# Uncertainty-Aware Camera Pose Estimation from Points and Lines

arXiv: https://arxiv.org/abs/2107.03890 · HTML: https://mlsanity.com/paper/2107.03890/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 50 references that are in the map.
- First posted on arXiv 8 Jul 2021.

## Builds on (most cited first, 5 of 5)

- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [Real-Time Seamless Single Shot 6D Object Pose Prediction](https://mlsanity.com/paper/1711.08848/) (2017)
- [MLPnP - A Real-Time Maximum Likelihood Solution to the Perspective-n-Point Problem](https://mlsanity.com/paper/1607.08112/) (2016)
- [Camera Pose Estimation from Lines using Pl"ucker Coordinates](https://mlsanity.com/paper/1608.02824/) (2016)

## Built on by (most cited first, 17 of 17)

- [Are we certain it's anomalous?](https://mlsanity.com/paper/2211.09224/) (2022)
- [Advances in Global Solvers for 3D Vision](https://mlsanity.com/paper/2602.14662/) (2026)
- [CPnP: Consistent Pose Estimator for Perspective-n-Point Problem with Bias Elimination](https://mlsanity.com/paper/2209.05824/) (2022)
- [DAC: Detector-Agnostic Spatial Covariances for Deep Local Features](https://mlsanity.com/paper/2305.12250/) (2023)
- [An Accurate and Real-time Relative Pose Estimation from Triple Point-line Images by Decoupling Rotation and Translation](https://mlsanity.com/paper/2403.11639/) (2024)
- [Generalized Maximum Likelihood Estimation for Perspective-n-Point Problem](https://mlsanity.com/paper/2408.01945/) (2024)
- [Optimal DLT-based Solutions for the Perspective-n-Point](https://mlsanity.com/paper/2410.14164/) (2024)
- [Variational Bayes for Federated Continual Learning](https://mlsanity.com/paper/2405.14291/) (2024)
- [Addressing the challenges of loop detection in agricultural environments](https://mlsanity.com/paper/2408.15761/) (2024)
- [LOSTU: Fast, Scalable, and Uncertainty-Aware Triangulation](https://mlsanity.com/paper/2311.11171/) (2023)
- [Research on a Camera Position Measurement Method based on a Parallel Perspective Error Transfer Model](https://mlsanity.com/paper/2602.07888/) (2026)
- [PCM-NeRF: Probabilistic Camera Modeling for Neural Radiance Fields under Pose Uncertainty](https://mlsanity.com/paper/2604.17831/) (2026)
- [Virtual-point-based Solutions to Handle Generalized Absolute Pose Problem](https://mlsanity.com/paper/2606.09294/) (2026)
- [Accuracy potential of visual localization exploiting high-end street-level imagery](https://mlsanity.com/paper/2607.24409/) (2026)
- [From Keypoints to Predictive Distributions: Post-Hoc Uncertainty for YOLO-Pose Models](https://mlsanity.com/paper/2607.26921/) (2026)
- [Protection Levels for Vision-Based Pose Estimation](https://mlsanity.com/paper/2608.10023/) (2026)
- [Observation Quality in DSM-Assisted Aerial Localization: A Benchmark and Base-Anchored Uncertainty Calibration](https://mlsanity.com/paper/2610.18564/) (2026)

## Abstract (arXiv)

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. The code is available at https://alexandervakhitov.github.io/uncertain-pnp/.