Search papers, labs, and topics across Lattice.
2
0
3
3
Forget clunky 2D-to-3D pipelines: Omni123 directly generates 3D models from text by cleverly using 2D image data as a geometric prior.
Scaling up avatar pre-training to 1M in-the-wild videos unlocks emergent generalization capabilities like relightability and garment support, even without direct supervision.
