US 12,333,638 B2
Generating images of object motion using one or more neural networks
Ting-Chun Wang, Santa Clara, CA (US); Tim Brooks, Berkeley, CA (US); Ming-Yu Liu, San Jose, CA (US); Tero Karras, Uusimaa (FI); and Jaakko Lehtinen, Uusimaa (FI)
Assigned to NVIDIA Corporaton, Santa Clara, CA (US)
Filed by Nvidia Corporation, Santa Clara, CA (US)
Filed on Nov. 9, 2021, as Appl. No. 17/522,776.
Prior Publication US 2023/0147641 A1, May 11, 2023
Int. Cl. G06T 7/20 (2017.01); G06N 3/045 (2023.01); G06T 13/00 (2011.01)
CPC G06T 13/00 (2013.01) [G06N 3/045 (2023.01)] 30 Claims
OG exemplary drawing
 
1. A processor, comprising:
one or more circuits to use one or more neural networks to generate one or more images of one or more objects based, at least in part, on user input indicating first motion of the one or more first objects and second motion of one or more second objects caused by the first motion.