Reconstruct a high-resolution (HR) image from a low-resolution (LR) using GM-GAN

Photo realistic single image super resolution using Generative Adversarial Network

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

A simple and customisable implementation of super-resolution paper. It allows further hyperparameters then what the paper suggests.

Astronomical image denoiser is a GAN model that can be used to denoise the noisy astronomical images obtained from space telescopes.

🔎 A minimal Tensorflow 2.0 implementation of SRGAN

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network - Modified for the ISRO Chandrayaan Lunar Mapping Challenge

This repository leverages Generative Adversarial Networks (GANs) to enhance image resolution for various applications, using the Super-Resolution GAN (SRGAN) architecture. The project includes a Jupyter Notebook for model training and a detailed research paper documenting the methodology and results.

Reimplementation of SRGAN

Tensor-Flow implementation of GAN trained on dataset of face images

Repository for (Un)Clear SoC Project, done in the Summer of 2021.

A deep-learning solution to improve the quality of low-resolution images. Improves the resolution of a 100x100 image to 400x400. This Library helps in optimizing data storage in cloud based servers without compromising much with the quality of the image. An Implementation of SRGAN (arXiv:1609.04802)

In this project, we implement SRGAN. This paper attempts to upscale images up to a factor of 4x without losing the finer textural details. We extended the scope of this idea to videos. We demonstrate that the model generalizes well on out-of-domain inputs through various biased and unbiased inputs.

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

Image Super Resolution using SRGAN on Tensorflow

Prototype of a Super-Resolution project.

Pixel x4 is a image super-resolution deep learning algorithm. It uses both the deep convolutional GANs for generating realistic images and the distance based loss function for creating visually similar images.

UGP 1 for 5th semester

Generate higher resolution images

Enhance single images with super-resolution GAN.