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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tao, Peilin, Cui, Hainan, Tu, Diantao, Shen, Shuhan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908433930780672
author Tao, Peilin
Cui, Hainan
Tu, Diantao
Shen, Shuhan
author_facet Tao, Peilin
Cui, Hainan
Tu, Diantao
Shen, Shuhan
contents 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2507_03306
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MGSfM: Multi-Camera Geometry Driven Global Structure-from-Motion
Tao, Peilin
Cui, Hainan
Tu, Diantao
Shen, Shuhan
Computer Vision and Pattern Recognition
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/.
title MGSfM: Multi-Camera Geometry Driven Global Structure-from-Motion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.03306