FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry
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 10.2M-sample multi-domain corpus with complementary local-detail supervision, yielding sharp boundaries and strong cross-domain generalization. Stage 2 moves beyond global scaling by introducing lightweight pixel-wise calibration fields for metric estimation: a scale field for spatially varying metric alignment and a ray-dire
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via arxiv author · 85%Muxin Liu →
“FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry”
- LinkedLinked via arxiv author · 85%Xiaoyang Lyu →
“FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry”
- LinkedLinked via arxiv author · 85%Tianhe Ren →
“FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry”
- LinkedLinked via arxiv author · 85%Peng Dai →
“FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry”
- LinkedLinked via arxiv author · 85%Xiaoshan Wu →
“FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry”
- LinkedLinked via arxiv author · 85%Zhiyue Zhang →
“FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry”
- LinkedLinked via arxiv author · 85%Jiaqi Zhang →
“FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry”
- LinkedLinked via arxiv author · 85%Jiehong Lin →
“FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry”