yarqian

Many thanks for your work. I am sorry to ask is it possible that the proposed patch matching method can be used for different image size for traning and testing.

Many thanks for your work. It seems that the mask network isn't implemented in this verson and there is a mask network as discribed in the paper, right?

Results on DnD dataset

1

I just run the code to test the result on the DnD dataset. Here are the results. I just want to know what is the problem. 0001_01_denoised.png 

Dear Haoyu Ma, Many thanks for your work. I am sorry to ask do you have the groud truth for defocused map and the sharp image in the test set?...