US 12,462,442 B2
Geolocation-based background generation for object images
Oleksandr Paliarush, Cedar Park, TX (US); Michele Saad, Austin, TX (US); Bingxuan Liang, Seattle, WA (US); and Saina Lajevardi, Austin, TX (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Aug. 28, 2023, as Appl. No. 18/238,749.
Prior Publication US 2025/0078323 A1, Mar. 6, 2025
Int. Cl. G06T 11/00 (2006.01); G06Q 30/0601 (2023.01)
CPC G06T 11/00 (2013.01) [G06Q 30/0643 (2013.01); G06T 2200/24 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method performed by one or more processing devices, comprising:
determining, by a geolocation module, a set of geolocations associated with a geographic region of interest, wherein each geolocation of the set of geolocations is mapped to context data associated with the geolocation;
generating, by a prompt generation module, multiple prompts based on the set of geolocations and the context data, wherein the prompt generation module comprises a first generative artificial intelligence (AI) model;
generating, by an image generation module, a set of background images based on the multiple prompts, wherein the image generation module comprises a second generative AI model; and
generating, by the image generation module, a plurality of synthetic images, wherein each synthetic image comprises a background image from the set of background images and an image of a target object.