多相机系统下，用几何约束提升三维重建精度与效率。
MGSfM: Multi-Camera Geometry Driven Global Structure-from-Motion
- 分层旋转平均+混合平移平均，利用相机刚性结构提升稳定性。
- 在大型数据集上精度媲美增量式方法，速度显著更快。
- 适合自动驾驶、机器人等真实场景的多相机三维重建。
多相机系统在自动驾驶和机器人环境感知中日益重要。其物理布局提供了固有的相对位姿约束，有助于结构光运动（SfM）重建。然而，传统全局SfM系统因优化框架脆弱而难以鲁棒运行。本文提出一种新型全局运动平均框架，包含两个核心模块：解耦旋转平均模块和混合平移平均模块。旋转平均采用分层策略，先估计刚性相机单元内的相对旋转，再计算全局刚性单元旋转。为增强平移平均的鲁棒性，同时引入相机-相机与相机-点约束，通过凸距离目标函数初始化相机位置与3D点，并以无偏非双线性角度目标函数进行精修。在大规模数据集上的实验表明，本系统在精度上达到或超过增量式SfM，同时显著提升效率。该框架优于现有全局SfM方法，适用于真实世界多相机SfM应用。代码已开源：https://github.com/3dv-casia/MGSfM/。
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。