googleartsculture / art-palette Goto Github PK

Hi!i

Firstly thanks for sharing this work! Im working on a similar problem with a different palette size - and im curious how you created the embedding for n=5 LAB color values to a 15 dimensional space. im assuming that you arent just doing a concatenation of the LAB values into a single 15 dimensional vector? 3 x 5 = 15 after all?

LAB is perceptually uniform and in theory should just work as Euclidean distance, but, trying it myself im not getting the best result and ive been trying other distance metrics like Hausdorff distance.

Looking at the embedding model in Netron it appears theres some biasing /learned weights changing the projection of an palette vector into a more usable perceptual embedding?

Can anyone shed any light as to how this was calculated / trained?

Thank you!

I want to use google art historic selfie API match who looks like you in china, I don't have any commercial or never earn money by this action, Just want to this technology to share china, Think about people will like it.