Dual-encoder networks using vision foundation models and synthetic data achieve accurate cross-view localization for rovers in aerial maps, validated on new real planetary analogue trajectories and synthetic image pairs with particle filter state estimation.
SAM 2: Segment Anything in Images and Videos
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Vision Foundation Models for Domain Generalisable Cross-View Localisation in Planetary Ground-Aerial Robotic Teams
Dual-encoder networks using vision foundation models and synthetic data achieve accurate cross-view localization for rovers in aerial maps, validated on new real planetary analogue trajectories and synthetic image pairs with particle filter state estimation.