Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,48 @@
|
|
1 |
---
|
2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- Super-Resolution
|
5 |
+
- computer-vision
|
6 |
+
- ESRGAN
|
7 |
+
- gan
|
8 |
---
|
9 |
+
|
10 |
+
### Model Description
|
11 |
+
[ESRGAN](https://arxiv.org/abs/2107.10833): ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution
|
12 |
+
|
13 |
+
[Paper Repo](https://github.com/xinntao/ESRGAN): Implementation of paper.
|
14 |
+
|
15 |
+
### Installation
|
16 |
+
```
|
17 |
+
pip install bsrgan
|
18 |
+
```
|
19 |
+
|
20 |
+
### BSRGAN Usage
|
21 |
+
```python
|
22 |
+
from bsrgan import BSRGAN
|
23 |
+
|
24 |
+
model = BSRGAN(weights='kadirnar/RRDB_ESRGAN_x4', device='cuda:0', hf_model=True)
|
25 |
+
model.save = True
|
26 |
+
|
27 |
+
pred = model.predict(img_path='data/image/test.png')
|
28 |
+
```
|
29 |
+
|
30 |
+
### BibTeX Entry and Citation Info
|
31 |
+
```
|
32 |
+
@inproceedings{zhang2021designing,
|
33 |
+
title={Designing a Practical Degradation Model for Deep Blind Image Super-Resolution},
|
34 |
+
author={Zhang, Kai and Liang, Jingyun and Van Gool, Luc and Timofte, Radu},
|
35 |
+
booktitle={IEEE International Conference on Computer Vision},
|
36 |
+
pages={4791--4800},
|
37 |
+
year={2021}
|
38 |
+
}
|
39 |
+
```
|
40 |
+
```
|
41 |
+
@InProceedings{wang2018esrgan,
|
42 |
+
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},
|
43 |
+
title = {ESRGAN: Enhanced super-resolution generative adversarial networks},
|
44 |
+
booktitle = {The European Conference on Computer Vision Workshops (ECCVW)},
|
45 |
+
month = {September},
|
46 |
+
year = {2018}
|
47 |
+
}
|
48 |
+
```
|