{"ID":2898268,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.03306","arxiv_id":"2507.03306","title":"MGSfM: Multi-Camera Geometry Driven Global Structure-from-Motion","abstract":"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/.","short_abstract":"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 optimizati...","url_abs":"https://arxiv.org/abs/2507.03306","url_pdf":"https://arxiv.org/pdf/2507.03306v1","authors":"[\"Peilin Tao\",\"Hainan Cui\",\"Diantao Tu\",\"Shuhan Shen\"]","published":"2025-07-04T05:25:00Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":612400,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2898268,"paper_url":"https://arxiv.org/abs/2507.03306","paper_title":"MGSfM: Multi-Camera Geometry Driven Global Structure-from-Motion","repo_url":"https://github.com/3dv-casia/MGSfM","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}