search

GuoShi28 / CBDNet

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

dateSet #17

Open shenyingying opened 5 years ago

shenyingying commented 5 years ago

can you share your dataset in training your model,there is some trouble in my reading the matlab code,is there anyone convert it to tensorflow ?

GuoShi28 commented 5 years ago

I have not converted all CBDNet code to python. However, I have released some ISP operator and inverse operators in python. You could refer to these codes to reproduce in python. Hope this helps.

shenyingying commented 5 years ago

thanks for your replay,there are some question confused me , can i consult you ?

  1. in denoise process,why should i evaluate the sigma value,can't i just find the mapping relation between real pic and clean pic ,this is my net: my training date : input : output: but the test result is :
  2. my final goal is realize the image enhancement and denoising ，the result i want just like the above training output ,is there any paper or net i can refer which you know ,thanks a lot .
GuoShi28 commented 5 years ago

@shenyingying Only utilize Cov layer without ReLU can not learn the task very well. Please notice more on details.