Comparison of contextual loss and perceptual loss

[zhangmozhe]

Hi I really like the paper. One question is that in your super-resolution paper you optimize the contextual loss with conv3_4 features. How about directly minimizing the perceptual loss for the conv3_4 features? What's the visual difference. Thanks!

[roimehrez]

What you suggested is exactly what the authors of SRGAN did. The perceptual quality is a bit less good. בתאריך יום ו׳, 15 ביוני 2018, 17:09, מאת zhangmozhe ‏< notifications@github.com>:

…

Hi I really like the paper. One question is that in your super-resolution paper you optimize the contextual loss with conv3_4 features. How about directly minimizing the perceptual loss for the conv3_4 features? What's the visual difference. Thanks! — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#8>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AOoKJtOArzL1ivWJHqVmHPNJMaYlMWkdks5t88AKgaJpZM4Upn6q> .