US 12,014,452 B2
Web-based digital image editing in real time utilizing a latent vector stream renderer and an image modification neural network
Akhilesh Kumar, San Jose, CA (US); Baldo Faieta, San Francisco, CA (US); Piotr Walczyszyn, Warsaw (PL); Ratheesh Kalarot, San Jose, CA (US); Archie Bagnall, Irvine, CA (US); Shabnam Ghadar, Menlo Park, CA (US); Wei-An Lin, San Jose, CA (US); Cameron Smith, Santa Cruz, CA (US); Christian Cantrell, Sterling, VA (US); Patrick Hebron, Briarcliff Manor, NY (US); Wilson Chan, San Jose, CA (US); Jingwan Lu, Santa Clara, CA (US); Holger Winnemoeller, Seattle, WA (US); and Sven Olsen, Victoria (CA)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Aug. 14, 2023, as Appl. No. 18/449,604.
Application 18/449,604 is a continuation of application No. 17/182,492, filed on Feb. 23, 2021, granted, now 11,727,614.
Prior Publication US 2023/0386114 A1, Nov. 30, 2023
Int. Cl. G06T 11/60 (2006.01); G06N 3/04 (2023.01); G06T 11/20 (2006.01)
CPC G06T 11/60 (2013.01) [G06N 3/04 (2013.01); G06T 11/203 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, from a first computing device, a latent image vector extracted from a digital image;
receiving, from a second computing device, an indication of a user interaction to modify the digital image;
modifying the latent image vector in response to the indication of the user interaction to modify the digital image;
sending the modified latent image vector to the first computing device to cause the first computing device to generate a modified digital image utilizing an image modification neural network;
determining an image-differential metric reflecting a difference between the digital image and the modified digital image; and
providing the image-differential metric to the second computing device to cause the second computing device to render the modified digital image depicting an image modification from the image-differential metric.