AI RESEARCH
Geometry Matters: 3D Foundation Priors for Learning Semantic Correspondence
arXiv CS.CV
•
ArXi:2605.30093v1 Announce Type: new Foundation features from self-supervised vision models and text-to-image diffusion models have proven effective for semantic correspondence estimation. However, because these features are learned primarily from 2D image objectives, they lack explicit 3D awareness and often confuse symmetric object sides, repeated parts, and visually similar structures that are distinct in 3D. We