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

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

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

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

📷 [ECCV 2022] Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection

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。

DF2K dataset download script

Probabilistic Downscaling of Climate Variables Using Denoising Diffusion Probabilistic Models

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

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

[AAAI 2025] Official implementation of the paper "EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution".

PyTorch implementation of Single image super-resolution based on directional variance attention network (Pattern Recognition2022)

A tensorflow-based implementation of SISR using EDSR, SRResNet, and SRGAN

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".

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

PyTorch implementation of Frequency-based Enhancement Network for Efficient Super-Resolution. (IEEE Access2022)

CVPR 2021 Oral Paper PatchGenCN

PyTorch implementation of Uniwin("Image Super-resolution with Unified Window Attention".

figsr — a frequency-domain (FFT-based) SISR architecture. Enhances detail reconstruction and inference speed, combining the strengths of CNNs and Transformers while mitigating their core limitations.

Official repository of our works related to Super-Resolution of BVOC Emission Maps.

This repository is about my experiences and experiments on the single image super resolution task, which is about retrievaling a high resolution image from a low resolution image using deep learning.

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

GFISRv2 is an experimental super-resolution architecture that augments Inception-style branches with a learnable FFT block. The goal is to strengthen global context modeling while remaining efficient and easy to integrate into existing PyTorch projects.

Quality Guided Single Image Super-Resolution

🌃 Comparing AI super-resolution models with visual examples and runtime analysis for image upscaling and restoration.

Test basic super resolution methods with different optimization methods

PyTorch super-resolution model (OverNet) with RGB support and ONNX exporter (OverNet: Lightweight Multi-Scale Super-Resolution with Overscaling Network (WACV 2021))

A PyTorch implementation of SRCNN