DMFN

DMFN copied to clipboard

The question about DMFB

2

Hello, I have a question about the module of DMFB. In your paper, there is a convolution operation named conv-3 after adding the conv-3-1 and conv-3-2.However, I con not find...

hhheeexxxuuu

Tried to reproduce training from paper but results looks bad.

1

Hi, I trained on places2 dataset. The discriminator loss is always 0. The results look poor. I trained it for 2 epochs on 80% of places2 dataset. Adding a sample...

ofirkris

Code release

3

Hi, thanks for sharing this project, results look promising indeed - well done. Any plans to release the full pipeline of code and weights?

ofirkris

Doubt about the input of the mask to the local discriminator

2

Hi, the method described in the paper is really amazing! I am implementing your paper. I have a doubt about how should be patch or mask arrangement as an input...

freaky-perceptron

About network architecture

1

Hi, Congratulated for your team get the champion of AIM 2020 Image Inpainting Challenge.:) Your result is really good and I would like to reproduce it. After read your paper,...

janchen0611

Can i release the reproduction code ?

4

Hi, I rewrite the DMFN model from your paper since i cant wait to see it's result. I want to know if i have the right to release the code...

HannH

Hi! Your results look really promising! Any chance the code will be provided?

5

muxgt

The model architecture is Unet-based model, but why there is no any skip connection?

Reginald-L

Hello, please tell me how the LPIPS, PSNR and SSIM indicators in the paper are calculated. The three results are not output after the test  Thank you...

LYL-hub-source

can this model generate various results for one image and mask pair?

universewill