SceneAligner grounds floorplan localization in a reconstructed 3D scene by creating a density-map proxy and learning to align it with rasterized floorplans via a fine-tuned 2D foundation model.
Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision
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
-
SceneAligner: 3D-Grounded Floorplan Localization in the Wild
SceneAligner grounds floorplan localization in a reconstructed 3D scene by creating a density-map proxy and learning to align it with rasterized floorplans via a fine-tuned 2D foundation model.