3D Point-Guided Aerial-Ground Image Matching for Robust Multi-View Reconstruction

Matching and aligning ground and aerial images is critical for enhancing the accuracy and completeness of 3D reconstruction. However, significant differences in perspective and radiometric characteristics between aerial and ground images make this task highly challenging. Existing mesh-based approaches often overlook the geometric properties of 3D points in the SfM model and suffer from limited track length. To address these issues, we propose a 3D Point-Guided Matching (PGM) framework that leverages reconstructed 3D points to guide the matching between aerial and ground images. Our method introduces a 3D Point-Guided Transformer (PGT) to encode point coordinates into embeddings and integrate them into image features, enabling effective correspondence between synthetic aerial views and real ground images. In addition, we design a Transformer-based Regression Module (TRM) to refine matching positions within local windows, improving the accuracy of aerial-ground correspondences. Our pipeline reduces matching errors, enables long-track correspondences, and facilitates robust multi-view integration. Furthermore, we construct two challenging aerial-ground datasets to validate the effectiveness of our method in city-scale 3D reconstruction. Extensive experiments on public benchmarks and our datasets demonstrate that our framework significantly outperforms state-of-the-art methods in both matching accuracy and reconstruction quality.