super-resolution

Image Super-Resolution for Anime-Style Art

A High-Quality Real Time Upscaler for Anime Video

Video, Image and GIF upscale/enlarge(Super-Resolution) and Video frame interpolation. Achieved with Waifu2x, SRMD, RealSR, Anime4K, RIFE, CAIN, DAIN, Real-ESRGAN and ACNet.

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, wav2lip, picture repair, image editing, photo2cartoon, image style transfer, and so on.

A lossless video/GIF/image upscaler achieved with waifu2x, Anime4K, SRMD and RealSR. Started in Hack the Valley 2, 2018.

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

Official pytorch implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, etc. Also support StyleGAN2, DFDNet.

Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.

Awesome GAN for Medical Imaging

A collection of state-of-the-art video or single-image super-resolution architectures, reimplemented in tensorflow.

Tensorflow 2.x based implementation of EDSR, WDSR and SRGAN for single image super-resolution

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

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

Trainable models and NN optimization tools

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

Tensorflow implementation of the SRGAN algorithm for single image super-resolution

Benchmark and resources for single super-resolution algorithms

Learning Continuous Image Representation with Local Implicit Image Function, in CVPR 2021 (Oral)

A PyTorch implementation of SRGAN based on CVPR 2017 paper "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network"

Fast and Accurate One-Stage Space-Time Video Super-Resolution (accepted in CVPR 2020)

A tensorflow implementation of "Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network", a deep learning based Single-Image Super-Resolution (SISR) model.

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

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

Code of our winning entry to NTIRE super-resolution challenge, CVPR 2018

Torch implementation of "Enhanced Deep Residual Networks for Single Image Super-Resolution"

Efficient & Generic Video Super-Resolution