US 12,412,340 B2
Synthesizing three-dimensional shapes using latent diffusion models in content generation systems and applications
Karsten Julian Kreis, Vancouver (CA); Xiaohui Zeng, Toronto (CA); Arash Vahdat, San Mateo, CA (US); Francis Williams, Brooklyn, NY (US); Zan Gojcic, Zurich (CH); Or Litany, Sunnyvale, CA (US); and Sanja Fidler, Toronto (CA)
Assigned to Nvidia Corporation, Santa Clara, CA (US)
Filed by Nvidia Corporation, Santa Clara, CA (US)
Filed on May 19, 2023, as Appl. No. 18/320,716.
Claims priority of provisional application 63/344,004, filed on May 19, 2022.
Prior Publication US 2024/0005604 A1, Jan. 4, 2024
Int. Cl. G06T 17/20 (2006.01); G06V 10/44 (2022.01)
CPC G06T 17/20 (2013.01) [G06V 10/44 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
generating, using a first generative diffusion model, a shape latent representing a shape of a three-dimensional object;
generating, using a second generative diffusion model and the shape latent, a set of latent points representative of latent features of the three-dimensional object;
providing the shape latent and the set of latent points as input to a decoder network; and
receiving, from the decoder network, a point cloud comprising a set of points representative of the three-dimensional object.