US 12,450,870 B2
Classifying image styles of images based on procedural style embeddings
Devavrat Tomar, Ecublens Vaud (CH); and Aliakbar Darabi, Newcastle, WA (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by ADOBE INC., San Jose, CA (US)
Filed on Apr. 3, 2023, as Appl. No. 18/130,266.
Application 18/130,266 is a continuation of application No. 16/897,008, filed on Jun. 9, 2020, granted, now 11,620,330.
Prior Publication US 2023/0360362 A1, Nov. 9, 2023
Int. Cl. G06V 10/74 (2022.01); G06F 16/55 (2019.01); G06F 16/583 (2019.01); G06F 18/214 (2023.01); G06N 3/08 (2023.01); G06N 20/00 (2019.01); G06V 10/44 (2022.01)
CPC G06V 10/761 (2022.01) [G06F 16/55 (2019.01); G06F 16/5854 (2019.01); G06F 18/214 (2023.01); G06N 3/08 (2013.01); G06N 20/00 (2019.01); G06V 10/443 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A non-transitory computer readable medium storing computer-usable instructions that, when used by one or more processors, cause the one or more processors to perform operations comprising:
receiving one or more portions of a target image;
extracting a first set of features from the one or more portions of the target image, the first set of features correspond to an image style of the one or more portions;
based on the extracting, generating, via a machine learning model, an image style embedding that includes an indication of the first set of features;
based on the generating, applying a layer, of a plurality of layers, of the image style to a source image;
receiving a user request to modify the layer of the image style; and
responsive to the receiving of the user request, modifying the layer of the image style at the source image.