发表机构
Institute of Automation, Chinese Academy of Sciences; School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院自动化研究所; 中国科学院大学人工智能学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出HiSfM分层SfM框架，通过锚定支架的分层重建消除视觉歧义，在减少运行时间的同时提升重建完整性，解决传统SfM在重复对称结构下失效及计算成本高的问题。
AI 中文摘要
运动恢复结构（SfM）是稀疏三维重建的基础工具，在机器人学和视觉领域影响广泛，支持建图、定位和大规模场景建模。然而，传统流程在重复或对称结构导致的严重视觉歧义下常失效，且因冗余相机和约束产生高昂计算成本。本文提出HiSfM，一种分层由粗到细的SfM框架，通过支架构建提升鲁棒性与效率。HiSfM首先利用几何启发式形成强局部社区，再通过打包边不相交生成树（EDST）构建紧凑且强的骨架以连接社区，同时用双视图歧义消除器验证骨架边。我们在该经验证的骨架上重建稳定支架，作为锚点捕捉场景本质，随后通过高效配准和三角测量吸收剩余图像以进一步优化。在聚焦歧义的基准和通用数据集上的实验表明，HiSfM可防止歧义引发的失效，相比现有方法大幅减少运行时间，且比激进稀疏化方法提升了完整性。代码可在指定URL获取。
英文摘要
Structure-from-Motion (SfM) is a fundamental tool for sparse 3D reconstruction with broad impact in robotics and vision, supporting mapping, localization, and large-scale scene modeling. However, conventional pipelines often fail under hard visual ambiguity caused by repeated or symmetric structures, and incur heavy computational cost due to redundant cameras and constraints. We present HiSfM, a hierarchical coarse-to-fine SfM framework that improves robustness and efficiency through scaffold construction. HiSfM first forms strong local communities using geometrical induced heuristics, then connects communities with a compact yet strong skeleton by packing edge-disjoint spanning trees (EDST) while verifying skeletal edges with a two-view disambiguator. We reconstruct a stable scaffold on this verified skeleton, serving as an anchor to capture the essence of the scene, and subsequently absorb remaining images via efficient registration and triangulation for further refinements. Experiments on ambiguity-focused benchmarks and general datasets show that HiSfM prevents ambiguity-induced failures while substantially reducing runtime compared to previous methods, and improves completeness over aggressive sparsification methods. Code is available at https://github.com/3dv-casia/HiSfM.
