通过全局感知的边优先级，提升位姿图初始化精度与效率
Global-Aware Edge Prioritization for Pose Graph Initialization
- 用图神经网络预测边的全局可靠性，避免独立匹配偏差
- 基于优先级构建多最小生成树，使位姿图更紧凑可靠
- 适用于稀疏数据和高速场景，尤其在模糊图像中表现优异
位姿图是结构光流（SfM）的核心组件，图像作为节点，边表示相对位姿。由于几何验证成本高，SfM流程仅保留候选边的稀疏子集，因此初始化至关重要。现有方法依赖图像检索将每张图连接至其前k近邻，独立处理边对，忽略全局一致性。本文提出边优先级机制，按对SfM的贡献度排序候选边。方法包含三部分：(1) 使用SfM衍生监督训练图神经网络，预测全局一致的边可靠性；(2) 基于优先级的多最小生成树构建位姿图；(3) 连通性感知得分调节，强化弱连通区域并减小图直径。该全局引导初始化生成更可靠、更紧凑的位姿图，在稀疏和高速场景中提升重建精度，优于当前最优检索方法，在模糊场景中表现更优。代码与模型已开源。
原文摘要 · Abstract (English)
The pose graph is a core component of Structure-from-Motion (SfM), where images act as nodes and edges encode relative poses. Since geometric verification is expensive, SfM pipelines restrict the pose graph to a sparse set of candidate edges, making initialization critical. Existing methods rely on image retrieval to connect each image to its $k$ nearest neighbors, treating pairs independently and ignoring global consistency. We address this limitation through the concept of edge prioritization, ranking candidate edges by their utility for SfM. Our approach has three components: (1) a GNN trained with SfM-derived supervision to predict globally consistent edge reliability; (2) multi-minimal-spanning-tree-based pose graph construction guided by these ranks; and (3) connectivity-aware score modulation that reinforces weak regions and reduces graph diameter. This globally informed initialization yields more reliable and compact pose graphs, improving reconstruction accuracy in sparse and high-speed settings and outperforming SOTA retrieval methods on ambiguous scenes. The ode and trained models are available at https://github.com/weitong8591/global_edge_prior.
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。