# Gravity-aware partially calibrated absolute pose estimation from affine- or rotation-covariant features

arXiv: https://arxiv.org/abs/2608.20056 · HTML: https://mlsanity.com/paper/2608.20056/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 69 references that are in the map.
- First posted on arXiv 20 Aug 2026.

## Builds on (most cited first, 20 of 20)

- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Graph-Cut RANSAC](https://mlsanity.com/paper/1706.00984/) (2017)
- [Repeatability Is Not Enough: Learning Affine Regions via Discriminability](https://mlsanity.com/paper/1711.06704/) (2017)
- [An Efficient Algebraic Solution to the Perspective-Three-Point Problem](https://mlsanity.com/paper/1701.08237/) (2017)
- [A Minimal Solution for Two-view Focal-length Estimation using Two Affine Correspondences](https://mlsanity.com/paper/1706.01649/) (2017)
- [Making Affine Correspondences Work in Camera Geometry Computation](https://mlsanity.com/paper/2007.10032/) (2020)
- [Globally Optimal Relative Pose Estimation with Gravity Prior](https://mlsanity.com/paper/2012.00458/) (2020)
- [Learning to Make Keypoints Sub-Pixel Accurate](https://mlsanity.com/paper/2407.11668/) (2024)
- [Minimal Solutions for Relative Pose with a Single Affine Correspondence](https://mlsanity.com/paper/1912.10776/) (2019)
- [Homography from two orientation- and scale-covariant features](https://mlsanity.com/paper/1906.11927/) (2019)
- [Relative planar motion for vehicle-mounted cameras from a single affine correspondence](https://mlsanity.com/paper/1912.06465/) (2019)
- [Minimal Cases for Computing the Generalized Relative Pose using Affine Correspondences](https://mlsanity.com/paper/2007.10700/) (2020)
- [gDLS*: Generalized Pose-and-Scale Estimation Given Scale and Gravity Priors](https://mlsanity.com/paper/2004.02052/) (2020)
- [P1AC: Revisiting Absolute Pose From a Single Affine Correspondence](https://mlsanity.com/paper/2011.08790/) (2020)
- [Relative Pose from SIFT Features](https://mlsanity.com/paper/2203.07930/) (2022)
- [Are Minimal Radial Distortion Solvers Really Necessary for Relative Pose Estimation?](https://mlsanity.com/paper/2505.00866/) (2025)
- [A Minimal Solver for Relative Pose Estimation with Unknown Focal Length from Two Affine Correspondences](https://mlsanity.com/paper/2512.22833/) (2025)

## Abstract (arXiv)

Inertial measurement units (IMUs) are now standard in most consumer devices, such as smartphones, drones, and extended reality (XR) headsets. By fusing visual and inertial data, localization systems gain significantly in speed and robustness compared to vision-only or IMU-only approaches. However, traditional pose estimation methods fail to utilize the local geometric information embedded in feature descriptors like SIFT. Recent work has proved the advantages of leveraging this information for relative and absolute pose estimation, but its application to partially calibrated absolute pose estimation remains unexplored. In this paper, we derive novel constraints for joint estimation of absolute pose and focal length, making use of a gravity vector obtained from IMU data and the feature-induced local geometry, which we use to construct two efficient solvers: UP1PfAC, that operates given a single affine correspondence and UP2PfORI, which requires two orientation-covariant features. Unlike traditional, semi-calibrated absolute pose methods requiring four point correspondences, our solvers benefit from fewer samples and lower computational cost, simplifying robust estimation in modern RANSAC-like frameworks. We evaluate the proposed solvers against the state-of-the-art on large-scale public datasets and demonstrate that our method achieves fast and accurate localization and focal length estimation.