# MGSfM: Multi-Camera Geometry Driven Global Structure-from-Motion

arXiv: https://arxiv.org/abs/2507.03306 · HTML: https://mlsanity.com/paper/2507.03306/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 56 references that are in the map.
- First posted on arXiv 4 Jul 2025.

## Builds on (most cited first, 21 of 21)

- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [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)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving](https://mlsanity.com/paper/2303.09551/) (2023)
- [Global Structure-from-Motion Revisited](https://mlsanity.com/paper/2407.20219/) (2024)
- [Shonan Rotation Averaging: Global Optimality by Surfing SO(p)n](https://mlsanity.com/paper/2008.02737/) (2020)
- [Robust Camera Location Estimation by Convex Programming](https://mlsanity.com/paper/1412.0165/) (2014)
- [3D Visual Perception for Self-Driving Cars using a Multi-Camera System: Calibration, Mapping, Localization, and Obstacle Detection](https://mlsanity.com/paper/1708.09839/) (2017)
- [Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System](https://mlsanity.com/paper/1809.05477/) (2018)
- [MMPTRACK: Large-scale Densely Annotated Multi-camera Multiple People Tracking Benchmark](https://mlsanity.com/paper/2111.15157/) (2021)
- [Baseline Desensitizing In Translation Averaging](https://mlsanity.com/paper/1901.00643/) (2019)
- [Range Image-based LiDAR Localization for Autonomous Vehicles](https://mlsanity.com/paper/2105.12121/) (2021)
- [A Pose-only Solution to Visual Reconstruction and Navigation](https://mlsanity.com/paper/2103.01530/) (2021)
- [Multi-Camera Multiple 3D Object Tracking on the Move for Autonomous Vehicles](https://mlsanity.com/paper/2204.09151/) (2022)
- [OmniSLAM: Omnidirectional Localization and Dense Mapping for Wide-baseline Multi-camera Systems](https://mlsanity.com/paper/2003.08056/) (2020)
- [Revisiting Rotation Averaging: Uncertainties and Robust Losses](https://mlsanity.com/paper/2303.05195/) (2023)
- [Efficient Initial Pose-graph Generation for Global SfM](https://mlsanity.com/paper/2011.11986/) (2020)
- [MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment](https://mlsanity.com/paper/2112.01349/) (2021)
- [Efficient 2D-3D Matching for Multi-Camera Visual Localization](https://mlsanity.com/paper/1809.06445/) (2018)
- [Linear Global Translation Estimation with Feature Tracks](https://mlsanity.com/paper/1503.01832/) (2015)

## Abstract (arXiv)

Multi-camera systems are increasingly vital in the environmental perception of autonomous vehicles and robotics. Their physical configuration offers inherent fixed relative pose constraints that benefit Structure-from-Motion (SfM). However, traditional global SfM systems struggle with robustness due to their optimization framework. We propose a novel global motion averaging framework for multi-camera systems, featuring two core components: a decoupled rotation averaging module and a hybrid translation averaging module. Our rotation averaging employs a hierarchical strategy by first estimating relative rotations within rigid camera units and then computing global rigid unit rotations. To enhance the robustness of translation averaging, we incorporate both camera-to-camera and camera-to-point constraints to initialize camera positions and 3D points with a convex distance-based objective function and refine them with an unbiased non-bilinear angle-based objective function. Experiments on large-scale datasets show that our system matches or exceeds incremental SfM accuracy while significantly improving efficiency. Our framework outperforms existing global SfM methods, establishing itself as a robust solution for real-world multi-camera SfM applications. The code is available at https://github.com/3dv-casia/MGSfM/.