RoMa and XoFTR reach 3.0 px mean error on SAR-optical registration zero-shot, with deployment protocol affecting results more than matcher selection.
Mission critical–satellite data is a dis- tinct modality in machine learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
CONDITIONAL 2representative citing papers
MMLandmarks supplies 197k aerial and 329k ground images plus text and GPS for 18,557 landmarks to benchmark multimodal geo-spatial understanding.
citing papers explorer
-
Are Pretrained Image Matchers Good Enough for SAR-Optical Satellite Registration?
RoMa and XoFTR reach 3.0 px mean error on SAR-optical registration zero-shot, with deployment protocol affecting results more than matcher selection.
-
MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding
MMLandmarks supplies 197k aerial and 329k ground images plus text and GPS for 18,557 landmarks to benchmark multimodal geo-spatial understanding.