Stars
Reverse Convolution and Its Applications to Image Restoration (ICCV, 2025)
"Denoising Diffusion Models for Plug-and-Play Image Restoration", Yuanzhi Zhu, Kai Zhang, Jingyun Liang, Jiezhang Cao, Bihan Wen, Radu Timofte, Luc Van Gool.
Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR
Official PyTorch code for Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution (MANet, ICCV2021)
Official PyTorch code for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021)
Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imaging, ICCV2021 [PyTorch Code]
Dynamic Attentive Graph Learning for Image Restoration, ICCV2021 [PyTorch Code]
Official Code for ICCV 2021 paper "Towards Flexible Blind JPEG Artifacts Removal (FBCNN)"
SwinIR: Image Restoration Using Swin Transformer (official repository)
Augmentations for Neural Networks. Implementation of Torchvision's transforms using OpenCV and additional augmentations for super-resolution, restoration and image to image translation.
traiNNer: Deep learning framework for image and video super-resolution, restoration and image-to-image translation, for training and testing.
Simple tutorials on Pytorch DDP training
Official PyTorch code for Flow-based Kernel Prior with Application to Blind Super-Resolution (FKP, CVPR2021)
This is the official implementation of "DHP: Differentiable Meta Pruning via HyperNetworks".
Blind Face Restoration via Deep Multi-scale Component Dictionaries (ECCV 2020)
Official SRFlow training code: Super-Resolution using Normalizing Flow in PyTorch
Deep Adaptive Inference Networks for Single Image Super-Resolution
A New Optimization Technique for Deep Neural Networks
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
Neural Blind Deconvolution Using Deep Priors (CVPR 2020)
This is the official website of our work 3D Appearance Super-Resolution with Deep Learning published on CVPR2019.
Project page of the CVPR2019 paper "Reliable and Efficient Image Cropping: A Grid Anchor based Approach"
Simultaneous Fidelity and Regularization Learning for Image Restoration (TPAMI 2019)
A PyTorch Implementation of "Learning a Single Convolutional Super-Resolution Network for Multiple Degradations"