US 12,136,151 B2
Generating collage digital images by combining scene layouts and pixel colors utilizing generative neural networks
Nadav Epstein, Berkeley, CA (US); Alexei A. Efros, Berkeley, CA (US); Taesung Park, Albany, CA (US); Richard Zhang, San Francisco, CA (US); and Elya Shechtman, Seattle, WA (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Feb. 14, 2022, as Appl. No. 17/650,957.
Prior Publication US 2023/0260175 A1, Aug. 17, 2023
Int. Cl. G06T 11/60 (2006.01); G06T 7/90 (2017.01)
CPC G06T 11/60 (2013.01) [G06T 7/90 (2017.01); G06T 2207/20084 (2013.01); G06T 2207/20212 (2013.01)] 14 Claims
OG exemplary drawing
 
8. A system comprising:
one or more memory devices comprising a digital image collaging neural network including an encoder neural network, a mask generator neural network, and a pixel generator neural network; and
one or more processors configured to cause the system to compose a combined digital image by:
generating encoded features for the combined digital image utilizing the encoder neural network;
determining a scene layout from the encoded features by utilizing the mask generator neural network to generate a digital image mask;
generating pixel colors from the encoded features utilizing the pixel generator neural network; and
generating, utilizing the digital image collaging neural network, the combined digital image depicting the scene layout in the pixel colors.