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.
Dinov2: Learning robust visual features with- out supervision, 2024
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative 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.
- AffordGen: Generating Diverse Demonstrations for Generalizable Object Manipulation with Afford Correspondence