Search papers, labs, and topics across Lattice.
2
0
4
0
Simple, artist-friendly quad meshes can now be automatically generated on 3D shapes using a diffusion model trained on a continuous surface representation, sidestepping the complexity of discrete mesh optimization.
VLMs are surprisingly bad at visually matching objects unless they can name them, revealing a critical reliance on textual anchors that overshadows their visual processing capabilities.
