---
license: apache-2.0
tags:
  - Super-Resolution
  - computer-vision
  - ESRGAN
  - gan
---

### Model Description
[ESRGAN](https://arxiv.org/abs/2107.10833): ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution

[Paper Repo](https://github.com/xinntao/ESRGAN): Implementation of paper.

### Installation
```
pip install bsrgan
```

### BSRGAN Usage
```python
from bsrgan import BSRGAN

model = BSRGAN(weights='kadirnar/RRDB_ESRGAN_x4', device='cuda:0', hf_model=True)
model.save = True

pred = model.predict(img_path='data/image/test.png')
```

### BibTeX Entry and Citation Info
```
@inproceedings{zhang2021designing,
    title={Designing a Practical Degradation Model for Deep Blind Image Super-Resolution},
    author={Zhang, Kai and Liang, Jingyun and Van Gool, Luc and Timofte, Radu},
    booktitle={IEEE International Conference on Computer Vision},
    pages={4791--4800},
    year={2021}
}
```
```
@InProceedings{wang2018esrgan,
    author = {Wang, Xintao and Yu, Ke and Wu, Shixiang and Gu, Jinjin and Liu, Yihao and Dong, Chao and Qiao, Yu and Loy, Chen Change},
    title = {ESRGAN: Enhanced super-resolution generative adversarial networks},
    booktitle = {The European Conference on Computer Vision Workshops (ECCVW)},
    month = {September},
    year = {2018}
}
```