# Efficient and Robust Absolute Pose Estimation via Gravity-Prior-Driven Transformation Decoupling and Pose Refinement

arXiv: https://arxiv.org/abs/2609.00713 · HTML: https://mlsanity.com/paper/2609.00713/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 85 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 23 of 23)

- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [TEASER: Fast and Certifiable Point Cloud Registration](https://mlsanity.com/paper/2001.07715/) (2020)
- [Back to the Feature: Learning Robust Camera Localization from Pixels to Pose](https://mlsanity.com/paper/2103.09213/) (2021)
- [Guaranteed Outlier Removal for Point Cloud Registration with Correspondences](https://mlsanity.com/paper/1711.10209/) (2017)
- [Large-scale, real-time visual-inertial localization revisited](https://mlsanity.com/paper/1907.00338/) (2019)
- [Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimization](https://mlsanity.com/paper/2007.14628/) (2020)
- [An Efficient Algebraic Solution to the Perspective-Three-Point Problem](https://mlsanity.com/paper/1701.08237/) (2017)
- [Embracing Events and Frames with Hierarchical Feature Refinement Network for Object Detection](https://mlsanity.com/paper/2407.12582/) (2024)
- [Outlier-Robust Estimation: Hardness, Minimally Tuned Algorithms, and Applications](https://mlsanity.com/paper/2007.15109/) (2020)
- [GOGMA: Globally-Optimal Gaussian Mixture Alignment](https://mlsanity.com/paper/1603.00150/) (2016)
- [Globally Optimal Relative Pose Estimation with Gravity Prior](https://mlsanity.com/paper/2012.00458/) (2020)
- [TurboReg: TurboClique for Robust and Efficient Point Cloud Registration](https://mlsanity.com/paper/2507.01439/) (2025)
- [Deterministic Approximate Methods for Maximum Consensus Robust Fitting](https://mlsanity.com/paper/1710.10003/) (2017)
- [SupeRANSAC: One RANSAC to Rule Them All](https://mlsanity.com/paper/2506.04803/) (2025)
- [Minimal Solutions for Panoramic Stitching Given Gravity Prior](https://mlsanity.com/paper/2012.00465/) (2020)
- [Efficient and Deterministic Search Strategy Based on Residual Projections for Point Cloud Registration with Correspondences](https://mlsanity.com/paper/2305.11716/) (2023)
- [URNet: Uncertainty-aware Refinement Network for Event-based Stereo Depth Estimation](https://mlsanity.com/paper/2509.18184/) (2025)
- [General techniques for approximate incidences and their application to the camera posing problem](https://mlsanity.com/paper/1903.07047/) (2019)
- [Trust Your IMU: Consequences of Ignoring the IMU Drift](https://mlsanity.com/paper/2103.08286/) (2021)
- [Transformation Decoupling Strategy based on Screw Theory for Deterministic Point Cloud Registration with Gravity Prior](https://mlsanity.com/paper/2311.01432/) (2023)
- [A Novel Method for the Absolute Pose Problem with Pairwise Constraints](https://mlsanity.com/paper/1903.10175/) (2019)
- [PoseGravity: Pose Estimation from Points and Lines with Axis Prior](https://mlsanity.com/paper/2405.12646/) (2024)

## Abstract (arXiv)

Estimation of the absolute pose of an object is an essential task for various robotic applications. Recently, incorporating gravity direction as prior information has emerged as a popular approach to simplify absolute pose estimation. However, developing a robust and efficient algorithm to solve this challenging problem remains a difficult question due to large amounts of mismatches. In addition, obtaining an accurate pose solution from selected inlier correspondences with gravity prior is still a research gap. In this paper, we propose a novel transformation strategy that exploits geometric relations derived from the gravity prior. Through transformation decoupling, the original 6 degrees of freedom (DoF) absolute pose estimation problem is simplified into a 4-DoFs problem: 1-DoF for the rotation angle and 3-DoFs for translation, significantly improving the efficiency. For the 1-DoF rotation angle, we apply a one-dimensional global voting algorithm for optimal estimation. Once the optimal rotation is obtained, the mismatched correspondences are preliminarily filtered, and translation estimation, a linear problem, can be easily solved. Furthermore, to obtain accurate pose results, we introduce a novel pose refinement algorithm to enhance the accuracy of both rotation and translation. Extensive experiments on synthetic data and three publicly available real-world datasets (TUM RGB-D, ETH3D, and RobotCar) demonstrate that the proposed method achieves stronger performance compared to existing state-of-the-art (SOTA) approaches. To further validate our method, we integrated it into ORB-SLAM2. The results on the KITTI dataset show it effectively reduces drift and improves trajectory alignment during relocalization. The source code will be released upon acceptance.