GuoShi28/CBDNet

Question about blur effect and noisy level map

MengXinChengXuYuan opened this issue · 2 comments

Hi I tried to reproduce the whole training procedure according to your paper
I set the level map as \sigma_c + \sigma_s*L and converted it to 0~1, and simply concat the map with rgb image as the input of blind denoise net

The training process is ok and I can get a good result on sidd or etc, when the noise is not very high.
However the denoised image is a little blurred, did you find this in your origin work?
Also when the noise getting higher the result gets worse, so I tried to give the noise level map a coefficient(x2) as mention in section 4.4 of the paper, but I found it just changed nothing. Even x2 gives barely any changes, which is more strange. I think if the noisy level map matters, giving a zero map should leads to a very bad denoise result right (as denoise ≈ input)?

In fact I've read the paper many times but I did't found how you take the noise map as input, am I right about concating it with the rgb image, or I just missed something? Also did you do any experiments about is? Like training a net without using the noise level map as a supervision (which means let LAMBasy = 0 and LAMBtv = 0), and compare the PSNR changes?

(1) The blur effect and not working well on some high noisy image. The denoising results may be over smoothing in some cases. These drawbacks may because that the realistic noise model may still have some difference compared with the real camera noise distribution, especially on some very noisy images.
(2) interactive denoising: In the paper, I try to multiply parameter (0.4~2) on the noise map and find it could change the denoising results. I am not sure of the reason for this problem.

Thank you for your response!
I wonder how did you take the noisy level map as an input to the blind denoise net?
Simply concat or pixel wise multiply with every channels with the rgb image?
Beside what's the approximate valve range for the noisy level map in your experiment? For me I converted the rgb valve to 0~1 and the noisy level map is around 0.02 to 0.08