Gizem Esra Unlu

Intermediate results during training

4

  I am training the network from scratch. Are the results above meaningful for epoch 65 on the test set? I will continue training until 300 epochs.

PatchGAN discriminator

1

Hello, Why are there fully connected layers at the end of the discriminator? Isn't the original PatchGAN architecture fully convolutional? I looked at the pytorch implementation of original DeblurGAN and...

Simplify from Manifold

1

Hi, thank you for the great library! I would like to ask three questions: 1) Do you have a simplification feature for ManifoldPlus; I have seen it on the original...

Intermediate results during training

1

Can you provide some intermediate deblurring results during training, eg, epoch 1,30,150 etc?

Hello, great work! When will you be releasing the dataset? Thank you.

20 km^2 3D Model

1

Thank you for this amazing dataset. I realized that only 1 km^2 is available for download from AccuCities website. How do we get all the corresponding 3D data for Holicity...

Instance-Guided Sampling

1

Dear author, Do you plan on providing instance-guided sampling code? Thank you.

Code Release

3

Dear Authors, Thank you for your inspiring work. Will there be a code release?

First of all, thank you for your work. It really helped me. My question is regarding the double discriminators used in the paper. If I am not wrong, There are...

Hello, what is mis_resblock? Why is its use compared to regular res_block? Thank you for sharing your work.