Cross3R performs feed-forward 3D reconstruction and 6-DoF pose estimation from any combination of satellite, UAV, and ground images, outperforming baselines on a new 278K-image tri-view dataset.
Uav-visloc: A large-scale dataset for uav visual localization
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 3roles
background 2polarities
background 2representative citing papers
SCC-Loc achieves 9.37 m mean localization error for UAV thermal images against satellite references, a 7.6-fold gain inside the 5 m threshold over prior methods, using a shared DINOv2 backbone plus three new semantic-consensus modules.
Introduces AnyVisLoc dataset and unified framework for UAV absolute visual localization, reports 74.1% accuracy within 5 m for best baseline, and proposes PDM@K retrieval metric.
citing papers explorer
-
Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images
Cross3R performs feed-forward 3D reconstruction and 6-DoF pose estimation from any combination of satellite, UAV, and ground images, outperforming baselines on a new 278K-image tri-view dataset.
-
SCC-Loc: A Unified Semantic Cascade Consensus Framework for UAV Thermal Geo-Localization
SCC-Loc achieves 9.37 m mean localization error for UAV thermal images against satellite references, a 7.6-fold gain inside the 5 m threshold over prior methods, using a shared DINOv2 backbone plus three new semantic-consensus modules.
-
Exploring the best way for UAV visual localization under Low-altitude Multi-view Observation Condition: a Benchmark
Introduces AnyVisLoc dataset and unified framework for UAV absolute visual localization, reports 74.1% accuracy within 5 m for best baseline, and proposes PDM@K retrieval metric.