Search papers, labs, and topics across Lattice.
D Mesh Initialization We extract a
2
0
3
2
Semantic correspondence gets a 3D boost: leveraging instance-specific 3D structure recovers from the 2D limitations of foundation models, significantly improving matching accuracy.
Deformable 3D reconstruction can be more than just visually plausible geometry; SEMAGIC shows it can also learn stable semantic correspondences, boosting performance by +14.7 PCK@0.1 on SPair-71k.
