US 12,223,623 B2
Harmonizing composite images utilizing a semantic-guided transformer neural network
He Zhang, San Jose, CA (US); and Hyun Joon Jung, Monte Sereno, CA (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Nov. 7, 2022, as Appl. No. 18/053,027.
Prior Publication US 2024/0161240 A1, May 16, 2024
Int. Cl. G06T 5/50 (2006.01); G06T 7/11 (2017.01); G06T 7/194 (2017.01); G06V 10/26 (2022.01); G06V 10/42 (2022.01); G06V 10/44 (2022.01); G06V 10/82 (2022.01)
CPC G06T 5/50 (2013.01) [G06T 7/11 (2017.01); G06T 7/194 (2017.01); G06V 10/267 (2022.01); G06V 10/42 (2022.01); G06V 10/44 (2022.01); G06V 10/82 (2022.01); G06T 2200/24 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20092 (2013.01); G06T 2207/20132 (2013.01); G06T 2207/20212 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving a composite image and a segmentation mask of a foreground object portrayed against a background of the composite image;
utilizing a global neural network branch to extract global information of the background;
utilizing a semantic neural network branch to extract semantic information from the composite image; and
generating a harmonized composite image comprising the foreground object harmonized with the background by decoding the global information and the semantic information.