Kai Zhang

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

DiffPIR. "Denoising Diffusion Models for Plug-and-Play Image Restoration", Yuanzhi Zhu, Kai Zhang, Jingyun Liang, Jiezhang Cao, Bihan Wen, Radu Timofte, Luc Van Gool.

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

MANet. Official PyTorch code for Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution (MANet, ICCV2021)

HCFlow. Official PyTorch code for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021)

SCI3D. Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imaging, ICCV2021 [PyTorch Code]

DAGL. Dynamic Attentive Graph Learning for Image Restoration, ICCV2021 [PyTorch Code]

FBCNN. Official Code for ICCV 2021 paper "Towards Flexible Blind JPEG Artifacts Removal (FBCNN)"

SwinIR. SwinIR: Image Restoration Using Swin Transformer (official repository)

augmennt. Augmentations for Neural Networks. Implementation of Torchvision's transforms using OpenCV and additional augmentations for super-resolution, restoration and image to image translation.

traiNNer. traiNNer: Deep learning framework for image and video super-resolution, restoration and image-to-image translation, for training and testing.

pytorch-distributed-training. Simple tutorials on Pytorch DDP training

FKP. Official PyTorch code for Flow-based Kernel Prior with Application to Blind Super-Resolution (FKP, CVPR2021)

PyTorchTricks. Some tricks of pytorch... :star:

dhp. This is the official implementation of "DHP: Differentiable Meta Pruning via HyperNetworks".

DFDNet. Blind Face Restoration via Deep Multi-scale Component Dictionaries (ECCV 2020)

SRFlow. Official SRFlow training code: Super-Resolution using Normalizing Flow in PyTorch

AdaDSR. Deep Adaptive Inference Networks for Single Image Super-Resolution

Gradient-Centralization. A New Optimization Technique for Deep Neural Networks

HLVC. Python

STGAN. STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing

SelfDeblur. Neural Blind Deconvolution Using Deep Priors (CVPR 2020)

3D_Appearance_SR. This is the official website of our work 3D Appearance Super-Resolution with Deep Learning published on CVPR2019.

Grid-Anchor-based-Image-Cropping. Project page of the CVPR2019 paper "Reliable and Efficient Image Cropping: A Grid Anchor based Approach"

n3net. Neural Nearest Neighbors Networks (NIPS*2018)

sfarl. Simultaneous Fidelity and Regularization Learning for Image Restoration (TPAMI 2019)

DnCNN-pytorch. DnCNN implement based on pytorch

ImageDenoising-DnCNN. Python

DnCNN-keras. Python

SRMD-pytorch. A PyTorch Implementation of "Learning a Single Convolutional Super-Resolution Network for Multiple Degradations"

RCAN. PyTorch code for our ECCV 2018 paper "Image Super-Resolution Using Very Deep Residual Channel Attention Networks"

mcnExtraLayers. Extra layers and utilities for matconvnet

STS-CNN. Q. Zhang, Q. Yuan, C. Zeng, X. Li, and Y. Wei, “Missing Data Reconstruction in Remote Sensing image with a Unified Spatial-Temporal-Spectral Deep Convolutional Neural Network,” IEEE TGRS, 2018.

RL-Restore. Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning (CVPR 2018 Spotlight)

MUNIT. Multimodal Unsupervised Image-to-Image Translation

OMoGMF. MATLAB

Shift-Net_pytorch. Pytorch implementation of Shift-Net: Image Inpainting via Deep Feature Rearrangement (ECCV, 2018)

xUnit. Learning a Spatial Activation Function for Efficient Image Restoration

MSWNNM. Multi-Scale Weighted Nuclear Norm Image Restoration

Shift-Net. Shift-Net: Image Inpainting via Deep Feature Rearrangement (ECCV, 2018)

DnCNN-PyTorch. PyTorch implementation of the TIP2017 paper "Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising"

pytorch-mcn. Convert models from MatConvNet to PyTorch

mcnPyTorch. Model converter (PyTorch -> MatConvNet)

RDN. Torch code for our CVPR 2018 paper "Residual Dense Network for Image Super-Resolution" (Spotlight)

STRCF. Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking (CVPR 2018)

MLKP. CVPR18 Paper: Multi-scale Location-aware Kernel Representation for Object Detection

TrimmedConvolution. C++

pytorch-zssr. PyTorch implementation of 1712.06087 "Zero-Shot" Super-Resolution using Deep Internal Learning

MIToolbox. Mutual Information functions for C and MATLAB

DeblurGAN. Image Deblurring using Generative Adversarial Networks

image_deblur_code. patch selection 1st

DnCNN. Implementation of DnCNN in MATLAB using Neural Network Toolbox™

vs_mxDnCNN. A mxnet implement of the paper "Beyond a Gaussian Denoiser : Residual Learning of Deep CNN for Image Denoising" for VapourSynth

hihca. Code for our ICCV 2017 paper "Higher-order Integration of Hierarchical Convolutional Activations for Fine-grained Visual Categorization"

BIQA_Toolbox. A benchmark implementation of representative deep BIQA models

DMSP. Deep Mean-Shift Priors for Image Restoration

deep-image-prior. Image restoration with neural networks but without learning.

DnCNN-caffe. A caffe implement of the TIP2017 paper Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

awesome-learning-based-image-processing. This is a collection of works on neural networks for low level image processing.

hdrnet. An implementation of 'Deep Bilateral Learning for Real-Time Image Enhancement', SIGGRAPH 2017

IBCCF. Matlab implementation of the IBCCF tracker.

Multi-views-fusion. LV Volumes Prediction based on Multi-views Fusion CNN

mcnDCGAN. Deep Convolution Generative Adversarial Networks for Matconvnet Toolbox

mcn-example-module. Example MatConvNet module with CPP/CUDA compilation

mcnRobustLoss. robust regression loss functions

RED. RED - Regularization by Denoising

WMMD-Caffe. C++

DLST. Deep Location-Specific Tracking

GAC_code_CGWS. This is the matlab code for GAC based on CGWS

DnCNN-tensorflow. :octocat::octocat:A tensorflow implement of the paper "Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising"

PRMLT. Matlab code of machine learning algorithms in book PRML

ProxImaL. A domain-specific language for image optimization.

Single-Image-Super-Resolution. A collection of high-impact and state-of-the-art SR methods

Image-Denoising-State-of-the-art.

SIR-CIR.

Iteration_bd. Learning Iteration-wise Generalized Shrinkage-Thresholding Operators for Blind Deconvolution (TIP 2016)

SCF. kernel Support Correlation Filter (KSCF)