You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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).
The text was updated successfully, but these errors were encountered:
@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:
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 why1
is necessary).The text was updated successfully, but these errors were encountered: