MatchCityLoc improves drone location using city shapes and angles

MatchCityLoc: Aerial Localization in LoD City Models via Surface Normal Matching

Computer Vision and Pattern Recognition

Summary

Finding exact drone locations in cities can be tough because GPS signals often don't work well between tall buildings. The authors designed MatchCityLoc to help drones figure out where they are by comparing the shapes and angles of roofs and walls seen from above with simple city models that don't have detailed textures. Instead of just matching building outlines, their method looks at the directions surfaces face, making it easier to find the right spot. This approach works well even with lightweight city data that protects privacy.

What this means in practice

  • For drone navigation teams: Enable drones to localize accurately in cities using lightweight city models without relying on GPS.
  • For urban mapping developers: Improve urban aerial mapping tools by integrating localization methods that use abstract city geometry instead of heavy textured models.

Authors

Oussema Dhaouadi, Zuria Bauer, Johannes Michael Meier, Marc Pollefeys, Daniel Cremers, Olaf Wysocki

Abstract

Autonomous Unmanned Aerial Vehicle (UAV) navigation in urban environments requires precise pose estimation. Because Global Navigation Satellite System (GNSS) signals are often unreliable in cities, visual localization serves as a crucial complement. Within this domain, textureless Level-of-Detail (LoD) city models provide a lightweight and privacy-preserving substitute for heavy 3D textured meshes. However, localizing against abstract geometry is challenging. Existing pipelines typically score 2D silhouette overlaps, which can suffer from severe geometric ambiguities. We present MatchCityLoc, a framework that shifts this paradigm to direct feature matching from a noisy 6-DoF pose prior. By extracting surface normals from the query image using a zero-shot foundation model and matching them against rendered LoD normals, we establish explicit 3D-to-2D correspondences. This enables a Perspective-n-Point (PnP) pose solve, which we iteratively refine through a render-and-match loop. Experiments demonstrate strong pose recall and accurate translation and rotation among the evaluated off-the-shelf LoD-based methods with very few renderings. By bridging the modality gap between aerial imagery and texture-free geometry, MatchCityLoc enables accurate localization using lightweight, privacy-preserving city models.