# Gravity-aligned Rotation Averaging with Circular Regression

arXiv: https://arxiv.org/abs/2410.12763 · HTML: https://mlsanity.com/paper/2410.12763/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 75 references that are in the map.
- First posted on arXiv 16 Oct 2024.

## Builds on (most cited first, 15 of 15)

- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [LaMAR: Benchmarking Localization and Mapping for Augmented Reality](https://mlsanity.com/paper/2210.10770/) (2022)
- [OpenVSLAM: A Versatile Visual SLAM Framework](https://mlsanity.com/paper/1910.01122/) (2019)
- [LDSO: Direct Sparse Odometry with Loop Closure](https://mlsanity.com/paper/1808.01111/) (2018)
- [Visual-Inertial Mapping with Non-Linear Factor Recovery](https://mlsanity.com/paper/1904.06504/) (2019)
- [Shonan Rotation Averaging: Global Optimality by Surfing SO(p)n](https://mlsanity.com/paper/2008.02737/) (2020)
- [A General Optimization-based Framework for Global Pose Estimation with Multiple Sensors](https://mlsanity.com/paper/1901.03642/) (2019)
- [NeuRoRA: Neural Robust Rotation Averaging](https://mlsanity.com/paper/1912.04485/) (2019)
- [AI-IMU Dead-Reckoning](https://mlsanity.com/paper/1904.06064/) (2019)
- [Convex Relaxations for Pose Graph Optimization with Outliers](https://mlsanity.com/paper/1801.02112/) (2018)
- [Revisiting Rotation Averaging: Uncertainties and Robust Losses](https://mlsanity.com/paper/2303.05195/) (2023)
- [Rotation Synchronization via Deep Matrix Factorization](https://mlsanity.com/paper/2305.05268/) (2023)
- [Comparison of modern open-source visual SLAM approaches](https://mlsanity.com/paper/2108.01654/) (2021)
- [A Decoupled and Linear Framework for Global Outlier Rejection over Planar Pose Graph](https://mlsanity.com/paper/2209.08543/) (2022)

## Built on by (most cited first, 3 of 3)

- [A Taxonomy of Structure from Motion Methods](https://mlsanity.com/paper/2505.15814/) (2025)
- [Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping](https://mlsanity.com/paper/2505.23756/) (2025)
- [G3T Up! Gravity Aligned Coordinate Frames Simplify Pointmap Processing](https://mlsanity.com/paper/2605.27372/) (2026)

## Abstract (arXiv)

Reconstructing a 3D scene from unordered images is pivotal in computer vision and robotics, with applications spanning crowd-sourced mapping and beyond. While global Structure-from-Motion (SfM) techniques are scalable and fast, they often compromise on accuracy. To address this, we introduce a principled approach that integrates gravity direction into the rotation averaging phase of global pipelines, enhancing camera orientation accuracy and reducing the degrees of freedom. This additional information is commonly available in recent consumer devices, such as smartphones, mixed-reality devices and drones, making the proposed method readily accessible. Rooted in circular regression, our algorithm has similar convergence guarantees as linear regression. It also supports scenarios where only a subset of cameras have known gravity. Additionally, we propose a mechanism to refine error-prone gravity. We achieve state-of-the-art accuracy on four large-scale datasets. Particularly, the proposed method improves upon the SfM baseline by 13 AUC@1^circ points, on average, while running eight times faster. It also outperforms the standard planar pose graph optimization technique by 23 AUC@1^circ points. The code is at https://github.com/colmap/glomap.