Search papers, labs, and topics across Lattice.
Affiliation:
4
0
5
Given multiple input images, this work predicts a point cloud in canonical space, deterministically inject the predicted geometry into the diffusion process through noise inversion, and modulate the resulting noise to preserve the generative flexibility required to complete unobserved regions and refine visible geometry.
Human-to-robot demonstration transfer notoriously collapses when tasks leave the 2D plane, but decoupling boundary keyframes from dense trajectory generation unlocks precise 3D flips and rotations across more than 1,200 objects.
New definitions of strong and weak anonymity reveal critical insights into privacy guarantees in discrete-event systems, challenging existing notions.
Ditch the finicky 3D geometry: OMGTex directly maps 2D face images to editable UV textures with a diffusion model, opening the door to robust facial texture reconstruction across diverse styles.
