search

GuoShi28 / CBDNet

Code for "Toward Convolutional Blind Denoising of Real Photographs", CVPR 2019
Apache License 2.0
501 stars 92 forks source link

Poisson-Gaussian noise implementation #41

Open xlying55 opened 4 years ago

xlying55 commented 4 years ago

Hi, I notice that the Poisson-Gaussian noise parameter are randomly sampled. How do you determine the 0.16 and 0.06 range for sigmas? I also read the implementation in the unprocessing paper, they use a quite smaller range (lower noise level).

GuoShi28 commented 3 years ago

Hi, when setting the sigmas, we choose a large range of noise levels to handle more noise images. For unprocessing paper, they set the range of sigma by the DND dataset. Thus the setting of our paper is wider.