US 11,727,614 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 Feb. 23, 2021, as Appl. No. 17/182,492.
Prior Publication US 2022/0270310 A1, Aug. 25, 2022
Int. Cl. G06T 11/60 (2006.01); G06T 11/20 (2006.01); G06N 3/04 (2023.01)
CPC G06T 11/60 (2013.01) [G06N 3/04 (2013.01); G06T 11/203 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A non-transitory computer readable medium comprising instructions that, when executed by a processing device, cause the processing device to perform operations comprising:
extracting a latent image vector from an initial digital image displayed via a client device;
receiving an indication of a user interaction to modify the initial digital image;
in response to the indication of the user interaction, determining an image-differential metric reflecting a difference between the initial digital image and a modified digital image generated by an image modification neural network based on a change within the latent image vector corresponding to the user interaction; and
providing the image-differential metric to the client device for rendering the modified digital image.