Blind Super-Resolution Kernel Estimation using an Internal-GAN

"KernelGAN"

(Official implementation)

Accepted NeurIPS 2019 (oral)

To run KernelGAN on all images in <input_image_path>:

python train.py --X4 --input-dir <input_image_path>

This will produce kernel estimations in the results folder

--X4 : Estimate the X4 kernel

--SR : Perform ZSSR using the estimated kernel

--real : Real-image configuration (effects only the ZSSR)

--output-dir : Output folder for the images (default is results)

Download the DIV2KRK dataset: dropbox

Reproduction code for your own Blind-SR dataset: github

Name		Name	Last commit message	Last commit date
Latest commit History 9 Commits
ZSSRforKernelGAN		ZSSRforKernelGAN
KernelGAN.yml		KernelGAN.yml
LICENSE		LICENSE
LICENSE.txt		LICENSE.txt
README.md		README.md
configs.py		configs.py
data.py		data.py
imresize.py		imresize.py
kernelGAN.py		kernelGAN.py
learner.py		learner.py
loss.py		loss.py
networks.py		networks.py
train.py		train.py
util.py		util.py