Real-ESRGAN

Real-ESRGAN

1. Colab Demo for Real-ESRGAN .
2. Portable Windows executable file. You can find more information here.

Real-ESRGAN aims for Practical Image Restoration.
We extend the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data.

:book: Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data

[Paper]   [Project Page]   [Demo]
Xintao Wang, Liangbin Xie, Chao Dong, Ying Shan
Applied Research Center (ARC), Tencent PCG
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences

We provide a pretrained model (RealESRGAN_x4plus.pth) with upsampling X4.
Note that RealESRGAN may still fail in some cases as the real-world degradations are really too complex.
Moreover, it may not perform well on human faces, text, etc, which will be optimized later.

---

We are cleaning the training codes. It will be finished on 23 or 24, July.

---

Portable executable files

You can download Windows executable files from https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN-ncnn-vulkan.zip

This executable file is portable and includes all the binaries and models required. No CUDA or PyTorch environment is needed.

You can simply run the following command:

./realesrgan-ncnn-vulkan.exe -i input.jpg -o output.png

Note that it may introduce block inconsistency (and also generate slightly different results from the PyTorch implementation), because this executable file first crops the input image into several tiles, and then processes them separately, finally stitches together.

This executable file is based on the wonderful Tecent/ncnn and realsr-ncnn-vulkan by nihui.

---

:wrench: Dependencies and Installation

• Python >= 3.7 (Recommend to use Anaconda or Miniconda)
• PyTorch >= 1.7

Installation

1. Clone repo

   git clone https://github.com/xinntao/Real-ESRGAN.git
   cd Real-ESRGAN
   

2. Install dependent packages

   # Install basicsr - https://github.com/xinntao/BasicSR
   # We use BasicSR for both training and inference
   pip install basicsr
   # pip install -r requirements.txt
   

:zap: Quick Inference

Download pre-trained models: RealESRGAN_x4plus.pth

Download pretrained models:

wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P experiments/pretrained_models

Inference!

python inference_realesrgan.py --model_path experiments/pretrained_models/RealESRGAN_x4plus.pth --input inputs

Results are in the results folder

BibTeX

@Article{wang2021realesrgan,
    title={Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data},
    author={Xintao Wang and Liangbin Xie and Chao Dong and Ying Shan},
    journal={arXiv:2107.10833},
    year={2021}
}

:e-mail: Contact

If you have any question, please email xintao.wang@outlook.com or xintaowang@tencent.com.