Real-ESRGAN
Image restoration toolkit
Develops algorithms for practical image and video restoration using synthetic data
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
29k stars
230 watching
4k forks
Language: Python
last commit: 7 months ago
Linked from 3 awesome lists
aminedenoiseesrganimage-restorationjpeg-compressionpytorchreal-esrgansuper-resolution
Related projects:
Repository | Description | Stars |
---|---|---|
| Software implementation of enhanced image restoration algorithm using Generative Adversarial Networks | 6,078 |
| An algorithm for restoring damaged or obscured faces in images | 36,009 |
| A GUI wrapper for Real-ESRGAN and Real-CUGAN image super-resolution algorithms | 500 |
| A tool that generates anime styles from landscape photos and videos using deep learning techniques. | 5,118 |
| Generates anime-style images from real-world photos using a deep learning model. | 4,502 |
| Image restoration toolbox with training and testing codes for various deep learning-based methods | 2,994 |
| This project trains deep CNN denoisers to improve image restoration tasks such as deblurring and demosaicking through model-based optimization methods. | 602 |
| A deep learning-based approach to super-resolution of degraded images. | 1,222 |
| A Python implementation of an image-to-image translation model for generating diverse images across multiple domains. | 3,513 |
| This repository provides code and models for a computer vision project that aims to improve the quality of videos by reducing motion blur. | 35 |
| An open-source software project that develops and provides tools for restoring degraded faces in images using Generative Pre-trained Networks. | 2,456 |
| Deblurring algorithm for videos using a neural network | 52 |
| A software framework for generating anime-style images through deep convolutional neural networks | 27,634 |
| A GAN-based system to generate anime faces using a custom dataset | 198 |
| An enhanced deep learning framework for image super-resolution tasks using Generative Adversarial Networks and PyTorch. | 151 |