While Structure from Motion (SfM) achieves great success in 3D reconstruction, it still meets challenges on large scale scenes. In this work, large scale SfM is deemed as a graph problem, and we tackle it in a divide-and-conquer manner. Firstly, the images clustering algorithm divides images into clusters with strong connectivity, leading to robust local reconstructions. Then followed with an image expansion step, the connection and completeness of scenes are enhanced by expanding along with a maximum spanning tree. After local reconstructions, we construct a minimum spanning tree (MinST) to find accurate similarity transformations. Then the MinST is transformed into a Minimum Height Tree (MHT) to find a proper anchor node and is further utilized to prevent error accumulation. When evaluated on different kinds of datasets, our approach shows superiority over the state-of-the-art in accuracy and efficiency. Our algorithm is open-sourced at this https URL.

中文翻译：

---

来自运动的基于图的并行大规模结构

虽然Structure from Motion (SfM) 在3D 重建方面取得了巨大成功，但在大规模场景中仍然面临挑战。在这项工作中，大规模 SfM 被视为图问题，我们以分而治之的方式解决它。首先，图像聚类算法将图像划分为具有强连通性的簇，从而实现稳健的局部重建。然后是图像扩展步骤，通过与最大生成树一起扩展来增强场景的连接性和完整性。在局部重建之后，我们构建一个最小生成树（MinST）来找到准确的相似变换。然后将 MinST 转换为最小高度树 (MHT) 以找到合适的锚节点，并进一步用于防止错误累积。在对不同类型的数据集进行评估时，我们的方法在准确性和效率方面优于最先进的方法。我们的算法在这个 https URL 上是开源的。