spedrox-sac/ESRGAN

ESRGAN_Model

This repository contains the ESRGAN (Enhanced Super-Resolution Generative Adversarial Network) model for high-quality image super-resolution. ESRGAN improves low-resolution images by reconstructing finer details, making it suitable for applications in image enhancement, restoration, and detail recovery.

ESRGAN (Enhanced SRGAN) Using [:rocket: [Real-ESRGAN] Model.

Quick Test

Dependencies

• Python 3
• Pytorch >= 1.0 (CUDA version >= 7.5 if installing with CUDA.More Details)
• Python packages: pip install numpy opencv-python

Test Models

1. Clone this github repo.

git clone https://huggingface.co/spedrox-sac/ESRGAN
cd ESRGAN

2. Place your own low-resolution images in ./LR folder. (There are two sample images - baboon and comic).
3. I've downloaded and fine tuned the model. But you can download pretrained models from Google Drive or Baidu Drive. Place the models in ./models. We provide two models with high perceptual quality and high PSNR performance (see model list).
4. Run test. We provide ESRGAN model and RRDB_PSNR model and you can config in the test.py.

 python test.py