Enhancing Anime Faces with SRGAN

SISR implementations

Sem 5 - Minor 1 - Projectno. 36 - JUET, Guna

Image reconstruction and captioning web application

OCR + Detect Documents + SRGAN

Comparative study of lightweight generator models (ESPCN, FSRCNN, IDN) in the SRGAN framework for Single Image Super-Resolution (SISR). Explore the trade-offs between performance and efficiency in GAN-based SISR.

Creating a dataset of varied celestial objects to get a broader perspective of Universe.

Implementation of Single Image Super Resolution using SRGAN

Readme file is inside the project folder itself. This repository contains SRGAN and ESRGAN with their model cards and training files. This was a final project of the course EE541 from USC.

Implementation of SRGAN from Scratch using PyTorch

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.

An implementation of srgan in pytorch with pytorch lightning

Image Super-Resolution using GAN

Super resolution of DSM

In SupeRAuGAN we implement a novel data augmentation technique tailored to Generative Adversarial Networks in order to reduce discriminator overfitting and stabilize training

Various GAN Model

A simple and complete implementation of super-resolution paper.