US 12,112,445 B2
Transferring geometric and texture styles in 3D asset rendering using neural networks
Kangxue Yin, Toronto (CA); Jun Gao, Toronto (CA); Masha Shugrina, Toronto (CA); Sameh Khamis, Alameda, 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 Sep. 7, 2021, as Appl. No. 17/467,792.
Prior Publication US 2023/0074420 A1, Mar. 9, 2023
Int. Cl. G06T 19/20 (2011.01); G06N 3/045 (2023.01); G06T 3/02 (2024.01); G06T 3/18 (2024.01); G06T 7/11 (2017.01); G06T 15/04 (2011.01); G06T 17/20 (2006.01)
CPC G06T 19/20 (2013.01) [G06N 3/045 (2023.01); G06T 3/02 (2024.01); G06T 3/18 (2024.01); G06T 7/11 (2017.01); G06T 15/04 (2013.01); G06T 17/20 (2013.01); G06T 2200/04 (2013.01); G06T 2207/20084 (2013.01); G06T 2219/2021 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method, comprising:
processing, using a trained first neural network, a source object to determine one or more source geometric features of the source object;
processing, using the trained first neural network, a target object to determine one or more target geometric features of the target object;
adjusting a selected source geometric feature based, at least in part, on the one or more target geometric features;
determining an output texture by adjusting a source texture corresponding to the source object based, at least in part, on a target texture corresponding to the target object; and
generating, based at least in part on the adjusted selected source geometric feature and the output texture, an output object.