US 12,493,991 B2
Recovering gamut color loss utilizing lightweight neural networks
Hoang M. Le, Toronto (CA); Michael S. Brown, Toronto (CA); Brian Price, San Jose, CA (US); and Scott Cohen, Sunnyvale, CA (US)
Assigned to Adobe Inc., San Jose, CA (US); and York University, Toronto (CA)
Filed by Adobe Inc., San Jose, CA (US); and York University, Toronto (CA)
Filed on Nov. 7, 2022, as Appl. No. 18/053,111.
Prior Publication US 2024/0161344 A1, May 16, 2024
Int. Cl. G06T 7/90 (2017.01); G06T 11/00 (2006.01)
CPC G06T 7/90 (2017.01) [G06T 11/001 (2013.01); G06T 2207/10024 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30168 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
identifying out-of-gamut pixel values of a digital image in a first gamut, wherein the digital image is converted to the first gamut from a second gamut;
determining target pixel values of a target version of the digital image in the first gamut that correspond to the out-of-gamut pixel values;
training a neural network to predict the target pixel values of the target version in the first gamut based on the out-of-gamut pixel values; and
embedding the neural network within the digital image in the second gamut.