US 12,439,173 B2
System and method of white balancing a digital image with multiple light sources
Mahmoud Afifi, North York (CA); Michael Brown, Toronto (CA); and Marcus Brubaker, Toronto (CA)
Filed by Mahmoud Afifi, North York (CA); Michael Brown, Toronto (CA); and Marcus Brubaker, Toronto (CA)
Filed on Sep. 7, 2022, as Appl. No. 17/930,213.
Claims priority of provisional application 63/242,649, filed on Sep. 10, 2021.
Prior Publication US 2023/0098058 A1, Mar. 30, 2023
Int. Cl. H04N 23/88 (2023.01); G06T 3/40 (2006.01); G06T 7/90 (2017.01); G06V 10/82 (2022.01)
CPC H04N 23/88 (2023.01) [G06T 3/40 (2013.01); G06T 7/90 (2017.01); G06V 10/82 (2022.01); G06T 2207/10024 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method for white balancing an input digital image, comprising:
receiving the input digital image in an input color space;
downsampling the input image to generate a downsampled image;
processing the downsampled image with a plurality of preset white balance settings to generate a plurality of downsampled images each with a distinct target white balance;
processing the input image at a fixed white balanced setting to produce an initial image;
inputting the white balanced downsampled images to a deep neural network to generate a weighting map, the weighting map comprising weights of the preset white balance settings at windows of the downsampled images;
generating a white balanced output image by determining a sum of the weighting map applied to mapped images each with a target white balance, the mapped images each determined by minimizing a residual sum of squares between the colors of the initial image and the downsampled image with the target white balance; and
outputting the white balanced output image.