US 12,322,167 B2
Computerized system and method for image creation using generative adversarial networks
Yueh-Ning Ku, Sunnyvale, CA (US); Mikhail Kuznetsov, New York, NY (US); Shaunak Mishra, New York, NY (US); and Paloma de Juan, New York, NY (US)
Assigned to YAHOO AD TECH LLC, New York, NY (US)
Filed by YAHOO AD TECH LLC, Dulles, VA (US)
Filed on Dec. 28, 2021, as Appl. No. 17/563,146.
Prior Publication US 2023/0206614 A1, Jun. 29, 2023
Int. Cl. G06V 10/82 (2022.01); G06N 3/02 (2006.01); G06T 5/50 (2006.01); G06T 5/77 (2024.01); G06T 7/11 (2017.01); G06V 10/26 (2022.01); G06V 10/46 (2022.01); G06V 10/88 (2022.01)
CPC G06V 10/82 (2022.01) [G06N 3/02 (2013.01); G06T 5/50 (2013.01); G06T 5/77 (2024.01); G06T 7/11 (2017.01); G06V 10/26 (2022.01); G06V 10/462 (2022.01); G06V 10/88 (2022.01)] 17 Claims
OG exemplary drawing
 
7. A method comprising:
retrieving a first image corresponding to a domain, the first image including a first salient object;
retrieving a domain relevant dataset corresponding to the domain, the domain relevant dataset including a plurality of second images, the second images having second salient objects;
ranking the plurality of second images based on a similarity measure of each second image to the first image;
selecting a subset of second images from the plurality of second images based on the ranking;
generating a set of segmented backgrounds by removing the second salient objects from each second image from the subset of second images, each of the segmented background of the set of segmented backgrounds having removed pixels;
generating a set of target backgrounds by inpainting the removed pixels of each segmented background of the set of segmented backgrounds; and,
generating a set of third images each image of the set of third images including the first salient object and a target background from the set of target backgrounds by aligning a shape and a center mass of a mask of the first salient object to a mask of each of the second salient objects of the second images of the subset of second images.