Pixel-wise Geo-registration of Drone and Satellite Images

Cross-view geo-registration is the task of aligning a queryimage to a geodetically accurate reference (e.g., satellite image), so thateach query pixel maps to a real-world GPS coordinate. Most existingwork addresses the related problem of cross-view geo-localization, wherethe goal is typically to estimate the camera center using retrieval, classi-fication, matching, or regression. Because these approaches do not pro-vide dense supervision, they are poorly suited for learning and eval-uating pixel-wise alignment. We introduce SkyReg, a geometry-awaregeo-registration model that estimates the transformation between thequery and reference images by explicitly modeling the 3D scene ge-ometry. Applying this transformation to warp the query into the ref-erence frame yields pixel-wise geo-localization, without relying on 2Dpoint matches, and remains robust to occlusions and large viewpointchanges. To enable training and standardized evaluation, we release (i)SkyReg-Train, a large-scale dataset of drone–satellite images annotatedwith per-pixel GPS coordinates, depth maps, and camera parameters de-rived from LiDAR and structure-from-motion, and (ii) SkyReg-Bench, aheld-out benchmark of unseen Urban and Suburban scenes with the samedense annotations. SkyReg achieves state-of-the-art performance againststrong retrieval and homography baselines, demonstrating the value ofgeometry-aware models and dense geodetic benchmarks for cross-viewgeo-registration. Dataset available at https://parthpk.github.io/skyreg-webpage.