Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models
Geometric foundation models, such as the Visual Geometry Grounded Transformer (VGGT), provide strong 3D priors from unposed images. However, such models operate purely in a feed-forward, deterministic regime, \ie~they cannot generate plausible geometry beyond what the input views directly support. Generative models for 3D scenes, on the other hand, must rely on strong geometric priors to produce coherent outputs from sparse inputs. We bridge these two paradigms by performing flow matching directly in VGGT's latent space, leveraging its learned 3D priors without committing to any explicit downs
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%Lisa Weijler →
“Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models”
- LinkedLinked via arxiv author · 85%Irene Ballester →
“Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models”
- LinkedLinked via arxiv author · 85%Guofeng Mei →
“Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models”
- LinkedLinked via arxiv author · 85%Tolga Birdal →
“Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models”
- LinkedLinked via arxiv author · 85%Pedro Hermosilla →
“Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models”