GitHub - Mrhc159/SCUNet: Practical Blind Denoising via Swin-Conv-UNet and Data Synthesis (Machine Intelligence Research 2023)

Codes

python main_models.py --models "SCUNet" --model_dir "model_zoo"

Gaussian denoising

python main_test_scunet_gray_gaussian.py --model_name scunet_gray_25 --noise_level_img 25 --testset_name set12

python main_test_scunet_color_gaussian.py --model_name scunet_color_25 --noise_level_img 25 --testset_name bsd68

Blind real image denoising

python main_test_scunet_real_application.py --model_name scunet_color_real_psnr --testset_name real3

python main_test_scunet_real_application.py --model_name scunet_color_real_gan --testset_name real3

Name		Name	Last commit message	Last commit date
Latest commit History 50 Commits
figs		figs
model_zoo		model_zoo
models		models
results		results
testsets		testsets
utils		utils
LICENSE		LICENSE
README.md		README.md
cog.yaml		cog.yaml
main_download_pretrained_models.py		main_download_pretrained_models.py
main_test_scunet_color_gaussian.py		main_test_scunet_color_gaussian.py
main_test_scunet_gray_gaussian.py		main_test_scunet_gray_gaussian.py
main_test_scunet_real_application.py		main_test_scunet_real_application.py
predict.py		predict.py