A hierarchical matcher combining DINOv2 semantic features with lightweight keypoint matching improves UAV-to-satellite localization success rate from about 0.5 to over 0.8 on the AerialVL and new CS-UAV benchmarks.
Exploring Deep Learning-Based Visual Localization Techniques for UA Vs in GPS-Denied Environments,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Hierarchical Image Matching for UAV Absolute Visual Localization via Semantic and Structural Constraints
A hierarchical matcher combining DINOv2 semantic features with lightweight keypoint matching improves UAV-to-satellite localization success rate from about 0.5 to over 0.8 on the AerialVL and new CS-UAV benchmarks.