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

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

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

Learning a Single Convolutional Super-Resolution Network for Multiple Degradations (CVPR, 2018) (Matlab)

动漫图片超分辨率（SISR）——基于WDSR (2019-4-30)

Code repo for "Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-Resolution" (CVPRW NTIRE2020).

A Novel Approach to Video Super-Resolution using Frame Recurrence and Generative Adversarial Networks | Python3 | PyTorch | OpenCV2 | GANs | CNNs

My implementaion of super-resolution based on dual-path networks. It can be used directly to reconstruct your low-resolution image to high-resolution. Also, you can use your dataset to train your networks

awesome super resoluiton paper collections w/o code including paper citation

Scripts to help easily create image pair datasets for super resolution models

A Keras implementation of a SISR (Single-Image Super-Resolution) Residual-CNN.

A curated list of awesome image super resolution

Sentinel-5P Single-Image Super-Resolution Toolbox

A collection of custom Super-Resolution models and restoration experiments.

lots of single image super resolution model implementations in tensorflow

This repository contains source code implementation of assignments for NTU's MSAI course AI6126 on Advanced Computer Vision (2020 Sem 1).

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.

Graduation Project. Applying Generative Adversarial Networks(GAN) with Residual-In-Residual(RIR) blocks.

Source codes for LGAN

Natural and Realistic Single Image Super-Resolution with Explicit Natural Manifold Discrimination (CVPR, 2019) in pytorch

Dataset Forge - Your Dataset helper.

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.

AI-powered hospital management system with MedGemma VLM for automated chest disease analysis, role-based workflows (Nurse/Doctor/Admin), and Wavelet-HAT super-resolution for CXR enhancement.

paper "Adaptive Pixel Classification and Equivalent Large Kernels for Lightweight Image Super-Resolution" for ICME2025.

A solution of SISR that merges the ideas of SRGAN and Edge Informed SISR. This solution was presented on 1st SpainAI hackathon obtain 4th position.

Super resolution

An implementation of SISR

A simple desktop utility for upscaling images using various models. Primarily adapted for digital art upscaling tasks.

Production-grade Single Image Super-Resolution framework in pure PyTorch

SRGAN (Super-Resolution Generative Adversarial Network) model for SISR (Single Image Super-Resolution) task using PyTorch