PPCN

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #ai #typescript #llm #go #golang #android #machine-learning #rust #deep-learning #linux

(★ 55)

Tensorflow implementation of Perception-Preserving Convolutional Networks for Image Enhancement on Smartphones (ECCV 2018 Workshop PIRM)

PPCN Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

![Python 3.5](https://img.shields.io/badge/python-3.5-green.svg)
# PPCN (Team: Rainbow)
[[Paper_download]](files/PPCN.pdf)[[Paper_CVF]](http://openaccess.thecvf.com/content_ECCVW_2018/papers/11133/Hui_Perception-Preserving_Convolutional_Networks_for_Image_Enhancement_on_Smartphones_ECCVW_2018_paper.pdf)[[Paper_Springer]](https://link.springer.com/chapter/10.1007/978-3-030-11021-5_13)
## Super-Resolution Task

 <img src="files/SR-pipeline.png" width="400"> 
 The schematics of the proposed network for image super-resolution

### Training

First, download the [DIV2K dataset](https://data.vision.ee.ethz.ch/cvl/DIV2K/) and unzip it in ``train_SR/`` folder.

Run the following command to train the SR model
```
python train_SR.py
```

### Testing

First, download the [SR_Test_Datasets](https://drive.google.com/open?id=1_K6mchwDGOQMIXuBIGrlDA4EAYgbtdmU) and put them in ``test/SR_test_data`` folder.

Run the following command to super-resolve low-resolution images

```
python evaluate_super_resolution.py
```
## Enhancement Task

 <img src="files/example.png" width="600"> 
 DPED image enhanced by our method 


 <img src="files/Generator.png" width="300">
 <img src="files/Discriminator.png" width="400"> 
 The structure of the proposed generator and discriminator for image enhancement

### Training
- Step1: download the pre-trained [VGG19 model](https://drive.google.com/open?id=1-09iLDLPB_evodnpTgq66u5YhvzN-kqo) and put it into `train/vgg_pretrained/` folder
- Step2: download [DPED dataset](http://people.ee.ethz.ch/~ihnatova/#dataset) and extract it into `train/dped/` folder.
- Step3: train the teacher model by executing the following command
```bash
python train_teacher.py
```
- Step4: train the student model by running
```bash
python train_student.py
```

### Testing

Run the following command to enhance low-quality images
```
python evaluate_enhancement.py
```
## Citation

If you find PPCN useful in your research, please consider citing:

```
@inproceedings{Hui-PPCN-2018,
  title={Perception-Preserving Convolutional Networks for Image Enhancement on Smartphones},
  author={Hui, Zheng and Wang, Xiumei and Deng, Lirui and Gao, Xinbo},
  booktitle={ECCV Workshop},
  pages = {197--213},
  year={2018}
}
```

## Code References
[1]https://github.com/aiff22/ai-challenge

[2]https://github.com/aiff22/DPED

[3]https://github.com/roimehrez/contextualLoss

PPCN

PPCN Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

PPCN

PPCN Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README