Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models
- Published
- Source
- arXiv
- Paper number
- 687
- Field
- Computer Vision
- arXiv ID
- 2607.19120
Key points
- The authors discover that VGGT tokens live on the product manifold of four hyperspheres and apply Riemannian flow matching.
- Compared with Euclidean flow matching, the Riemannian version improves consistently on every metric, with about a 44 percent gain in LPIPS.
- It works with a single input view and is order invariant.
- It reduces Chamfer distance by more than 40 percent on ScanNet++ and by more than 70 percent on ETH3D.
- The generated 3D scans align with the context frame and enable consistent scene reconstruction.
Paper links
External research summaries. These are not HDATF publications or measured product results.