Color calibration giving poor results for white balance

[kofa (István Kovács)]

@123sg

I wonder if the “AI” could be a sort of translation error…?

The (AI) options are not real artificial intelligence, but it was shorter than spelling “optimization by machine-learning” in the list, and AI is all the rage now so pretty much anything a bit advanced qualifies for that name these days. They perform an auto-detection of the best illuminant in image.

Introducing color calibration module (formerly known as channel mixer rgb)

[Screenshot_20201109_024706] TL; DR : this is a full rewrite in clean unbounded RGB of the channel mixer in darktable. The old one had some computational mistakes in it, plus clipped RGB at 100%. This also introduces much requested normalization options, that will keep the sum of parameters to 1, trying to preserve – rougly – luminance (actually, perceptual luminance is much more than a simple sum of R + G + B, since it depends on hue, but… TL; DR). Ok. But it’s named color calibration becaus…

@123sg

always seem to end up at what seems like a default of 5002K

Aurélien has said (in one of his videos, or written somewhere) that a result close to 5000 K usually means the ‘AI’ method failed to determine the illuminant (set the correct white balance).