Kai Zhang

The function "vl_simplenn_tidy" is included in [Matconvnet](http://www.vlfeat.org/matconvnet/), so you should install [Matconvnet](http://www.vlfeat.org/matconvnet/install/) first. You can also test the model without Matconvnet by using the following but with much slower speed....

https://github.com/cszn/DPIR/issues/7#issuecomment-758504017

https://github.com/cszn/DPIR/issues/7#issuecomment-758504017

https://github.com/cszn/SRMD/tree/master/TrainingCodes

- We only need to train the denoiser models. - The training code can be obtained by modifying the code of FFDNet from [KAIR](https://github.com/cszn/KAIR/blob/master/main_train_ffdnet.py).

I will update the models in the next month.

, "pretrained_netG": "bsrgan_x4_gan/models/BSRNet.pth" // path of pretrained model , "pretrained_netD": null , "pretrained_netE": null

I will upload our original degradation model today. Real-ESRGAN follows our BSRGAN work. The idea of using double JPEG, double blur, down-up-resize, Gaussian noise for color image and grayscale image...

I have uploaded the degradation_bsrgan(). The idea of BSRGAN was mainly inspired by my previous work SRMD, DPSR, IRCNN, USRNet, DnCNN, FFDNet and CBDNet. For example, the degradation shuffle and...

As claimed in our paper, `One can conveniently modify the degradation model by changing the degradation parameter settings and adding more reasonable degradation types to improve the practicability for a...