single-image-super-resolution

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

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

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

A Fast Deep Learning Model to Upsample Low Resolution Videos to High Resolution at 30fps

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

天池2019阿里巴巴优酷视频增强和超分辨率挑战赛自用代码，EDVR、WDSR、ESRGAN三个模型。

Second-order Attention Network for Single Image Super-resolution (CVPR-2019)

TensorFlow Implementation of "Fast and Accurate Single Image Super-Resolution via Information Distillation Network" (CVPR 2018)

This repository includes code of training/testing of our work published in NTIRE-2020 workshop titled "Unsupervised Single Image Super-Resolution Network (USISResNet) for Real-World Data Using Generative Adversarial Network".

WSISR: Single image super-resolution for Whole slide Imaging using convolutional neural networks and self-supervised color normalization.

A simple convolutional neural network for single image super-resolution

Quality Guided Single Image Super-Resolution

TensorFlow implementation of "Accurate Image Super-Resolution Using Very Deep Convolutional Network" (CVPR 2016)

Test basic super resolution methods with different optimization methods

This repository stores scripts used to run COMASure and its extensions. The models are studied as part of the requirements for the MSc Data Science and Machine Learning dissertation at UCL.

Implementations of Single Image Super Resolution Models (EDSR, RDN, SRGAN and ESRGAN) using PyTorch

This project is aimed to develop powerful and lightweight networks to address the two tasks presented in the NTIRE 2017 SuperResolution Challenge. The two deep learning models proposed, i.e. a CNN and a GAN, achieved satisfactory results demonstrating an important ability in introducing high-frequency information to the original low resolution images.