全局运动恢复结构与前馈重建的结合
Global Structure-from-Motion Meets Feedforward Reconstruction
将前馈重建模型作为经典 SfM 流程中的组件（如初始化、匹配或失败场景兜底），在低纹理、弱重叠、对称场景下弥补经典 SfM 的失效，同时保留经典方法在标准场景下的精度与可扩展性；对做三维重建的人，这是一个可直接复用的混合式 pipeline 设计范式。
原文依据 propose a new Structure-from-Motion pipeline by combining the respective strengths of classical and feedforward methods
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论运动恢复结构——即从一组图像中同时估计相机位姿与三维场景结构的过程——仍是计算机视觉中的核心挑战，尚有许多未解问题。近期前馈三维重建的进展在克服经典 SfM 方法的顽固失效情形方面取得了显著进步，尤其是在低纹理、有限重叠和对称性为特征的场景中。然而，尽管前馈方法在这些困难条件下表现优异，它们往往在可扩展性、精度或鲁棒性方面存在局限，并且在标准重建设定下通常不及经典方法。在本工作中，我们系统分析了这些局限，并提出了一种新的运动恢复结构流程，融合经典方法与前馈方法各自的优势。在多个数据集上的大量实验表明了我们方法的优势，在广泛场景中取得了最优结果。我们将系统作为开源实现发布于 https://github.com/colmap/gluemap。
英文原文摘要 1116 字符
Structure-from-Motion -- the process of simultaneously estimating camera poses and 3D scene structure from a collection of images -- remains a central challenge in computer vision, with many open problems yet to be solved. Recent advances in feedforward 3D reconstruction have made significant strides in overcoming persistent failure cases of classical SfM methods, particularly in scenarios characterized by low texture, limited overlap, and symmetries. However, while feedforward approaches excel in these challenging conditions, they often face limitations regarding scalability, accuracy, or robustness, and typically fall short of classical methods in standard reconstruction settings. In this work, we systematically analyze these limitations and propose a new Structure-from-Motion pipeline by combining the respective strengths of classical and feedforward methods. Extensive experiments across multiple datasets show the benefits of our approach, achieving state-of-the-art results across a wide range of scenarios. We share our system as an open-source implementation at https://github.com/colmap/gluemap.