SatFix: Absolute Visual Localization of UAVs in Satellite Maps from a Single Oblique Image

Key points

• We propose SatFix, a feed-forward UAV--satellite localization framework built on VGGT-$Ω$.1
• Satellite-grid features act as queries that aggregate UAV visual evidence, and two lightweight heads regress a 3-DoF pose in the satellite-map frame: continuous 2D position and heading.1
• For metric evaluation, we introduce University-Metric, where satellite imagery is re-collected over a region up to 10.7$\times$ longer on a side (about 114$\times$ the ground area) than the original University-1652 tiles, with continuous position and heading labels for the original UAV tours.1
• With one UAV view, SatFix localizes 52.08% of test frames within 50 m and 17.34% within 10 m, with median position and heading errors of 45.66 m and $20.81^\circ$, respectively.1

Sources (1)

• [1]SatFix: Absolute Visual Localization of UAVs in Satellite Maps from a Single Oblique Image
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 01:01 AM

  We study absolute metric UAV localization within a provided geo-referenced satellite region, recovering continuous map position and viewing heading from a single oblique image or a short multi-view clip.

  We propose SatFix, a feed-forward UAV--satellite localization framework built on VGGT-$Ω$.

Extractive summary: sentences quoted from the sources.