Shi Guo

I have updated the license.

The python code does not provide the noise map. You can refer to the paper definition, sigma_s*img + sigma_c. sigma_s and sigma_c are obtained by the random function.

@ACEaaaaa, Hi, There are two things you need to confirm. (1) load model correctly. ``load('.\models\CBDNet.mat'); `` need to change to ``load('./models/CBDNet.mat');`` for linux. (2) [compile MatconvNet](http://www.vlfeat.org/matconvnet/install/) correctly. If you have...

In Python code, the clean image is converted to RAW and then convert back to the sRGB image. In my understanding, these artifact is caused by the demosaic process. In...

Sure. I will release my training code after I tied up the code. Actually, I have released the code of creating noise images for training, [Test_Realistic_Noise_Model.m](https://github.com/GuoShi28/CBDNet/blob/master/Test_Realistic_Noise_Model.m). You can use this...

In this paper, we did not consider camera-pipeline when estimating the noise map. In [AddNoiseMosai.m](https://github.com/GuoShi28/CBDNet/blob/master/utils/AddNoiseMosai.m), noise map can be simply set as ```sigma_n = noise_c_map + noise_s_map```.

Also to clear that, I make a mistake in the paper. Noise map should be defined as "L*\sigma_s + \sigma_c", not "x*\sigma_s + \sigma_c". The definition of L can be...

@XSLXANDY Hi, I did not count downsampling and upsampling layer in total 16 layers. There's no relu layer after downsampling layer which can be treated as a conv layer with...

Yes. L is the irradiance.

You can refer to a similar topic https://github.com/GuoShi28/CBDNet/issues/4. When training using synthesis noise image, we have ground-truth noise map. When training using real noise image, we do not have ground-truth...