Kai Zhang

KAIR. Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR

DnCNN. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP, 2017)

BSRGAN. Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (ICCV, 2021) (PyTorch) - We released the training code!

USRNet. Deep Unfolding Network for Image Super-Resolution (CVPR, 2020) (PyTorch)

DPSR. Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels (CVPR, 2019) (PyTorch)

SCUNet. Practical Blind Denoising via Swin-Conv-UNet and Data Synthesis (Machine Intelligence Research 2023)

DPIR. Plug-and-Play Image Restoration with Deep Denoiser Prior (IEEE TPAMI 2021) (PyTorch)

IRCNN. Learning Deep CNN Denoiser Prior for Image Restoration (CVPR, 2017) (Matlab)

FFDNet. FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising (TIP, 2018)

SRMD. Learning a Single Convolutional Super-Resolution Network for Multiple Degradations (CVPR, 2018) (Matlab)

ConverseNet. Reverse Convolution and Its Applications to Image Restoration (ICCV, 2025)

ColorFM. ECCV 2026

cszn.github.io. Kai's homepage:

cszn.