gaze_redirection

KO | EN

gitlite — search

#javascript #ai #llm #go #android #deep-learning #docker #macos #nodejs #awesome #cli #security #ios #openai

gaze_redirection

(★ 155)

[Official Implementation] Photo-Realistic Monocular Gaze Redirection Using Generative Adversarial Networks, He et.al. ICCV 2019

파일 탐색기

최종 버전 다운로드 (.zip)

- circle.gif
- framework.jpg
- headpose.jpg
- horizontal.gif
- vertical.gif
- zed.gif
- __init__.py
- archs.py
- data_loader.py
- model.py
- __init__.py
- ops.py
.gitignore
__init__.py
LICENSE
main.py
README.md

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Photo-Realistic Monocular Gaze Redirection Using Generative Adversarial Networks

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

[[Paper](https://arxiv.org/abs/1903.12530)] [[Video](https://www.youtube.com/watch?v=oHx88bHaM18)]

Authors: **Zhe He**, Adrian Spurr, Xucong Zhang, Otmar Hilliges

Contact: zhehe@student.ethz.ch

The following gifs are made of images generated by our method. For each GIF, the input is a still image.

Our method is also capable of handling different head poses.

## Note

The code here is the development version. It can be used for training, but there might be some redundant code and compatiblity issues. The final version will be released soon.

## Dependencies

tensorflow == 1.7  
 numpy == 1.13.1  
 scipy == 0.19.1

## Dataset

The dataset contains eye patch images parsed from [Columbia Gaze Dataset](http://www.cs.columbia.edu/~brian/projects/columbia_gaze.html). It can be downloaded via this [link](https://drive.google.com/file/d/1tE3QfFjxtRco4ruLZwYyUhjyYSp2QIJL/view?usp=sharing).

```Bash
tar -xvf dataset.tar
```

The dataset contains six subfolders, N30P/, N15P/, 0P/, P15P/, P30P/ and all/. Prefix 'N' means negative head pose, and 'P' means positive head pose. Folder all/ contains all eye patch images with different head poses.

## VGG-16 pretrained weights

```Bash
wget http://download.tensorflow.org/models/vgg_16_2016_08_28.tar.gz .
tar -xvf vgg_16_2016_08_28.tar.gz
```

## Train

```Bash
python main.py --mode train --data_path ./dataset/all/ --log_dir ./log/ --batch_size 32 --vgg_path ./vgg_16.ckpt
```

## Test

To test the model on frontal faces, run the following command.

```Bash
python main.py --mode eval --data_path ./dataset/0P/ --log_dir ./log/ --batch_size 21
```

Then, a folder named **eval** will be generated in folder **./log/**. Generated images, input images and target images will be stored in **eval/**.

gaze_redirection

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

gaze_redirection

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README