Hajo Nils Krabbenhöft

The fact that the patch for type 1 noise just made the noise change its shape shows me that there must be a strong pressure for the network to learn...

 To verify the border guess, I trained a model with cropping and then applied it without cropping. Already after 1100 iterations, the model has completely "un-learned" the features necessary...

 For testing my theory on noise type 2, I artificially introduced 0-values into the model after c3. As expected, very strong patterns show up on the transition from normal...

Wow that's a great result :) I just fell into another gotcha: It seems the current lambda_tv value is dependent on the image size.

Just by the function `F.sum(F.convolution_2d(x, W=wh) ** 2) + F.sum(F.convolution_2d(x, W=ww) ** 2)` you can see that the results of the convolution are squared and summed up, but not divided...

@jackieyung for that model, which lambda_feat and lambda_style did you use?

In addition to the things I reported before, I just also found another cause of noise for very bright or very dark areas: The chainer batch normalization function will always...

In my testing, the early normalization reduces noisy overexposure a bit, but it didn't help with the dots. My working guess is that the dots are either the result of...

I agree that the normalization order is probably not important enough to warrant breaking old models. But my hope is that we'll also be able to figure out the dot...

Another difference to the paper seems to be that they add reflection padding before starting the processing chain and then crop the image before VGG evaluation. That way, the border...