MapAnything automates 3D geo-localization of urban assets from monocular images via metric depth estimation combined with geometric calculations, with validation against LiDAR point clouds.
The mapillary vistas dataset for semantic understanding of street scenes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MapAnything: Evaluating Monocular Metric Depth Models for 3D Urban Asset Localization
MapAnything automates 3D geo-localization of urban assets from monocular images via metric depth estimation combined with geometric calculations, with validation against LiDAR point clouds.