Global-Aware Edge Prioritization for Pose Graph Initialization
This work addresses a critical bottleneck in SfM pipelines for computer vision applications, offering a novel approach to enhance pose graph construction, though it appears incremental as it builds upon existing methods with global consistency improvements.
The paper tackles the problem of pose graph initialization in Structure-from-Motion by proposing a global-aware edge prioritization method that ranks candidate edges based on their utility, resulting in more reliable and compact pose graphs that improve reconstruction accuracy in sparse and high-speed settings and outperform state-of-the-art retrieval methods on ambiguous scenes.
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.