US 12,462,440 B2
Image-based searches for templates
Brian Eriksson, San Jose, CA (US); Wei-ting Hsu, San Jose, CA (US); Santiago Pombo, San Francisco, CA (US); Sandilya Bhamidipati, Mountain View, CA (US); Rida Khan, Saratoga, CA (US); Ravali Devarapalli, San Jose, CA (US); Maya Christmas Davis, San Francisco, CA (US); Lam Wing Chan, Sunnyvale, CA (US); Konstantin Blank, Seattle, WA (US); Jason Omid Kafil, Los Angeles, CA (US); and Di Ni, San Jose, CA (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Nov. 16, 2022, as Appl. No. 17/988,377.
Prior Publication US 2024/0161347 A1, May 16, 2024
Int. Cl. G06T 11/00 (2006.01); G06V 10/70 (2022.01)
CPC G06T 11/00 (2013.01) [G06V 10/768 (2022.01); G06T 2200/24 (2013.01); G06T 2210/22 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
generating, by a processing device using a machine learning model, an embedding vector that represents a semantic intent of an input digital image;
identifying, by the processing device, templates based on distances between embedding vector representations of semantic intent of the templates and the embedding vector that represents the semantic intent of the input digital image;
determining, by the processing device, a template of the identified templates based on a distance between an embedding vector representation of a semantic intent of a candidate digital image included in the template and the embedding vector that represents the semantic intent of the input digital image; and
generating, by the processing device, an output digital image for display in a user interface that depicts the determined template as having the candidate digital image being replaced by the input digital image.