A semantic feature optimization grounds disconnected partial 3D reconstructions to geospatially accurate reference models derived from Google Earth, improving global alignment across classical and learning-based pipelines.
The reference model First we extract DINOv2 [38] dense features per rendered landmark image from Google Earth Studio
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
-
Scene Grounding In the Wild
A semantic feature optimization grounds disconnected partial 3D reconstructions to geospatially accurate reference models derived from Google Earth, improving global alignment across classical and learning-based pipelines.