Single Image Super-Resolution (SISR) with SRResNet, EDSR and SRGAN

Overview

Single Image Super-Resolution (SISR) with SRResNet, EDSR and SRGAN

Result

Introduction

Image super-resolution (SR) is the process of recovering high-resolution (HR) images from low-resolution (LR) images. It is an important class of image processing techniques in computer vision and image processing and enjoys a wide range of real-world applications, such as medical imaging, satellite imaging, surveillance and security, astronomical imaging, amongst others.

With the advancement in deep learning techniques in recent years, deep learning-based SR models have been actively explored and often achieve state-of-the-art performance on various benchmarks of SR. A variety of deep learning methods have been applied to solve SR tasks, ranging from the early Convolutional Neural Networks (CNN) based method to recent promising Generative Adversarial Nets based SR approaches.

A more detailed overview on single image super-resolution is given in this paper.

This repo contains a tensorflow-based implementation of:

Model Architecture

SRResNet

SRResNet adopts the design of ResNet to solve issues with training very deep models. it managed to achieve state-of-the-art performance when it came out. it contains 16 residual blocks and uses mean squared error as a loss function Here’s an overview of the SRResNet architecture:

EDSR

One super-resolution model that follows this high-level architecture is described in the paper Enhanced Deep Residual Networks for Single Image Super-Resolution (EDSR). It is a winner of the NTIRE 2017 super-resolution challenge. They further improved the performance by employing a better ResNet structure: Batch Normalization layers are removed, and instead of mean squared error, mean absolute error is used as a loss function. Here’s an overview of the EDSR architecture:

SRGAN

SRGAN further improves the results of SRResNet by fine-tuning its weights so that it can generate high frequency details in the generated image. This is done by training the model in a GAN using Perceptual loss function , which consists of two components:

  • Content Loss: compares deep features extracted from SR and HR images with a pre-trained VGG network. With φi,j we indicate the feature map obtained by the j-th convolution (after activation) before the i-th maxpooling layer within the VGG19 network

Here Wi,j and Hi,j describe the dimensions of the respective feature maps within the VGG network.

  • Adversarial Loss: The GAN descriminator D is optimized for descriminating SR from HR images whereas the generator is optimized for generating more realistic SR images in order to fool the discriminator.

Perceptual loss is the weighted sum of content loss and adversarial loss:

And here's an overview of the discriminator architecture:

This project aims to fine-tune EDSR model instead of SRResNet in the same manner.

Results

Environment setup

# using pip
pip install -r requirements.txt

# using Conda
conda create --name 
   
     --file requirements.txt

   

Training and testing

You can try training the models yourself by executing train.py

python train.py

This will download DIV2K dataset, preprocess it and start training EDSR then fine-tuning it in SRGAN.

If you want to train the model with different dataset, pass its path as an argument.

python train.py 
   

   

the dataset directory should have a 'HR' folder which contains high resolution images, and a 'LR' folder which contains low resolution images.

And if you'd like to test out model on an image, you can execute resolve_image.py and pass the image path as an argument. The output will be saved in the 'results' directory

python resolve_image.py 
   

   
You might also like...
A framework for joint super-resolution and image synthesis, without requiring real training data
A framework for joint super-resolution and image synthesis, without requiring real training data

SynthSR This repository contains code to train a Convolutional Neural Network (CNN) for Super-resolution (SR), or joint SR and data synthesis. The met

MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution (CVPR2021)

MASA-SR Official PyTorch implementation of our CVPR2021 paper MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Re

PyTorch implementation of Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution, IJCNN 2021.

GCResNet PyTorch implementation of Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution, IJCNN 2021. The code will

Unofficial pytorch implementation of the paper "Dynamic High-Pass Filtering and Multi-Spectral Attention for Image Super-Resolution"

DFSA Unofficial pytorch implementation of the ICCV 2021 paper "Dynamic High-Pass Filtering and Multi-Spectral Attention for Image Super-Resolution" (p

Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel
Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel

Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel This repository is the official PyTorch implementation of BSRDM w

Using image super resolution models with vapoursynth and speeding them up with TensorRT

vs-RealEsrganAnime-tensorrt-docker Using image super resolution models with vapoursynth and speeding them up with TensorRT. Also a docker image since

Paper Title: Heterogeneous Knowledge Distillation for Simultaneous Infrared-Visible Image Fusion and Super-Resolution

HKDnet Paper Title: "Heterogeneous Knowledge Distillation for Simultaneous Infrared-Visible Image Fusion and Super-Resolution" Email: 18186470991@163.

Official implementation of the paper 'Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution'
Official implementation of the paper 'Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution'

DASR Paper Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution Jie Liang, Hui Zeng, and Lei Zhang. In arxiv preprint. Abs

Repository for
Repository for "Exploring Sparsity in Image Super-Resolution for Efficient Inference", CVPR 2021

SMSR Reposity for "Exploring Sparsity in Image Super-Resolution for Efficient Inference" [arXiv] Highlights Locate and skip redundant computation in S

Owner
Interested in Ai, machine learning and data analysis.
null
Cours d'Algorithmique Appliquée avec Python pour BTS SIO SISR

Course: Introduction to Applied Algorithms with Python (in French) This is the source code of the website for the Applied Algorithms with Python cours

Loic Yvonnet 0 Jan 27, 2022
PyTorch code for our ECCV 2020 paper "Single Image Super-Resolution via a Holistic Attention Network"

HAN PyTorch code for our ECCV 2020 paper "Single Image Super-Resolution via a Holistic Attention Network" This repository is for HAN introduced in the

五维空间 140 Nov 23, 2022
Practical Single-Image Super-Resolution Using Look-Up Table

Practical Single-Image Super-Resolution Using Look-Up Table [Paper] Dependency Python 3.6 PyTorch glob numpy pillow tqdm tensorboardx 1. Training deep

Younghyun Jo 116 Dec 23, 2022
PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)

About PyTorch 1.2.0 Now the master branch supports PyTorch 1.2.0 by default. Due to the serious version problem (especially torch.utils.data.dataloade

Sanghyun Son 2.1k Jan 1, 2023
pytorch implementation for Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802

PyTorch SRResNet Implementation of Paper: "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network"(https://arxiv.org/abs

Jiu XU 436 Jan 9, 2023
Torch implementation of "Enhanced Deep Residual Networks for Single Image Super-Resolution"

NTIRE2017 Super-resolution Challenge: SNU_CVLab Introduction This is our project repository for CVPR 2017 Workshop (2nd NTIRE). We, Team SNU_CVLab, (B

Bee Lim 625 Dec 30, 2022
PyTorch code for 'Efficient Single Image Super-Resolution Using Dual Path Connections with Multiple Scale Learning'

Efficient Single Image Super-Resolution Using Dual Path Connections with Multiple Scale Learning This repository is for EMSRDPN introduced in the foll

null 7 Feb 10, 2022
Augmentation for Single-Image-Super-Resolution

SRAugmentation Augmentation for Single-Image-Super-Resolution Implimentation CutBlur Cutout CutMix Cutup CutMixup Blend RGBPermutation Identity OneOf

Yubo 6 Jun 27, 2022
Official PyTorch code for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021)

Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021) This repository is the official P

Jingyun Liang 159 Dec 30, 2022
Official PyTorch code for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021)

Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021) This repository is the official P

Jingyun Liang 159 Dec 30, 2022