Is there any reason why you normalize only input, but not gt?

[DongHwanJang]

I believe that if you use the global residual connection, you need to normalize both of them.
Unless, the residual term has to learn much more complicated space.

[dingyan1478]

Hi!
I have the same question. Do you understand now?

[Alienvoid]

Maybe the convolutional network automatically learns the reversal normalization such that it produces the clean image without normalizing the gt.

[Wangbk-dl]

Hi, I have the same question. Do you get any idea?

[DongHwanJang]

@Wangbk-dl No. I guess there was a mistake implementing the code.

[LT1st]

Error while implementing the code.