-
Notifications
You must be signed in to change notification settings - Fork 148
Open
Description
I believe the original paper means that we want the source image to mimic the color performance of the target image, and output a transferred source image. However, in your implementation, the target image is instead transferred. This is what makes the following formulas inconsistent with the paper.
color_transfer/color_transfer/__init__.py
Lines 50 to 68 in 6724ccf
| l -= lMeanTar | |
| a -= aMeanTar | |
| b -= bMeanTar | |
| if preserve_paper: | |
| # scale by the standard deviations using paper proposed factor | |
| l = (lStdTar / lStdSrc) * l | |
| a = (aStdTar / aStdSrc) * a | |
| b = (bStdTar / bStdSrc) * b | |
| else: | |
| # scale by the standard deviations using reciprocal of paper proposed factor | |
| l = (lStdSrc / lStdTar) * l | |
| a = (aStdSrc / aStdTar) * a | |
| b = (bStdSrc / bStdTar) * b | |
| # add in the source mean | |
| l += lMeanSrc | |
| a += aMeanSrc | |
| b += bMeanSrc |
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels