Wrong loss function in paper/poster?

[LiranPo]

Hi,
I believe the paper and poster both show a loss function with contradictive parts: the first part (Lab) gets bigger as images are more different, whereas the second part (MS-SSIM) gets bigger as images are more similar.

The code, however, does not make that mistake, and actually the loss is Lab + (1 - MS-SSIM) (not sure why 1 is necessary).

[sjmoran]

Hi @LiranPo, thank you for highlighting this typo - you are correct the loss should be Lab + (1-MS-SSIM) in the paper and in the poster.

[LiranPo]

@sjmoran another note about the poster (screenshot above) - I believe you mean Lab and MS-SSIM account for global and local enhancement, respectively, not vice versa, as stated in your paper: