US 11,887,217 B2
Text editing of digital images
Paridhi Maheshwari, Bhopal (IN); Vishwa Vinay, Bangalore (IN); Shraiysh Vaishay, Jhansi (IN); Praneetha Vaddamanu, Hyderabad (IN); Nihal Jain, Andheri (IN); and Dhananjay Bhausaheb Raut, Aurangabad (IN)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Oct. 26, 2020, as Appl. No. 17/079,844.
Prior Publication US 2022/0130078 A1, Apr. 28, 2022
Int. Cl. G06T 11/00 (2006.01); G06F 40/30 (2020.01); G06V 10/40 (2022.01)
CPC G06T 11/001 (2013.01) [G06F 40/30 (2020.01); G06V 10/40 (2022.01); G06T 2207/10024 (2013.01); G06T 2207/20081 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by a processing device, a text user input describing a visual object and a visual attribute, the visual object specifying a visual context of the visual attribute;
generating, by the processing device, a feature representation that includes a color profile based on the visual context of the text user input using a generator, the generator trained as part of a generative adversarial network using training text and training feature representations generated from training digital images located based on an image search performed using the training text;
editing, by the processing device, a digital image based on the feature representation; and
outputting, by the processing device, the edited digital image for display in a user interface.