arXiv cs.CV
· Papers
FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry
arXiv:2607.11588v1 Announce Type: new Abstract: We present FoundationGeo, a two-stage framework that explicitly bridges relative and metric prediction via spatial calibration and principled data design. Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3 and training on a curated