Question about constant terms C1, C2.

[SaulZhang]

From the original paper, C1=(KL)², but I didn't see L=255 just K1 = 0.01 in the specific implementation of the code. Can the item L be discarded?Does the code mean K1=0.01?

[LiUzHiAn]

I have the same question. If my images are normalized into [-1,1] or [0,1], should I have to modify the c_1 and c_2 constant?

@SaulZhang, How about your use situation? Thx~

[LiUzHiAn]

@SaulZhang Well, I find another multi-scale SSIM repo implementation, which is based on this repo exactly. There, the variable L is taken into consideration. For the 0-255 gray image, L is set to be 255. For [-1,1] range, L is set to be 2.

Link is: https://github.com/jorge-pessoa/pytorch-msssim/blob/master/pytorch_msssim/init.py. Check it out !