Sefi Kligler
Sefi Kligler
I didn't understand you are waiting on me... Regarding the idea: mathematically, if you pass a delta kernel (1 in the center and zero otherwise) through a sequence of kernels...
Regarding "theory" - it is nothing complicated. We are suppressing linear operations - we can definitely represent a sequence of convolutions as one. I don't have a proof for that...
@ZhuoranLyu - Thank you for the assistance - that is definitely true
> Can you provide the code for making DIV2KRK? [link](https://github.com/assafshocher/BlindSR_dataset_generator) > Besides, except the blur kernel, I want to know whether you add the noise to the DIV2K to form...
You referred to this also in a different issue - please keep them in a single place! Regarding the code - I will have to check if it happens to...
We created a synthetic dataset we named DIV2KRK by downscaling HR images with random kernels. These random kernels are the GT kernels we compare to. For more info regarding DIV2KRK,...
Sorry but you are "missing something"... All we take is the LR images that were generated using random kernels from the HR images. Both HR and kernel are UNKNOWN to...
Yes - the GT kernel is from the repo. I am not familiar with DPED dataset - care to share the link?
Sorry I can't understand. What are you trying to do?
yes, you can do that. KernelGAN estimates the kernel that relates the input image to it's SR image. So given an image + kernel (estimated by KernelGAN) - if you...