https://github.com/1adrianb/2d-and-3d-face-alignment
This repository implements a demo of the networks described in "How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)" paper.
https://github.com/1adrianb/2d-and-3d-face-alignment
3d-face-alignment computer-vision deeplearning face-alignment torch7
Last synced: about 1 month ago
JSON representation
This repository implements a demo of the networks described in "How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)" paper.
- Host: GitHub
- URL: https://github.com/1adrianb/2d-and-3d-face-alignment
- Owner: 1adrianb
- License: other
- Created: 2017-03-16T15:22:43.000Z (about 8 years ago)
- Default Branch: master
- Last Pushed: 2018-02-26T14:26:28.000Z (about 7 years ago)
- Last Synced: 2025-03-28T05:12:02.611Z (about 1 month ago)
- Topics: 3d-face-alignment, computer-vision, deeplearning, face-alignment, torch7
- Language: Lua
- Homepage: https://www.adrianbulat.com/face-alignment
- Size: 38.1 KB
- Stars: 961
- Watchers: 56
- Forks: 209
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# How far are we from solving the 2D \& 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)
This repository implements a demo of the networks described in "How far are we from solving the 2D \& 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)" paper. Please visit [our](https://www.adrianbulat.com) webpage or read bellow for instructions on how to run the code and access the dataset.
**Training code: **
**:fire: Python code available: **
Note: If you are interested in a binarized version, capable of running on devices with limited resources please also check for a demo.
## Requirments
- Install the latest [Torch7](http://torch.ch/docs/getting-started.html) version (for Windows, please follow the instructions available [here](https://github.com/torch/distro/blob/master/win-files/README.md))
- Install python 2.7.x
### Lua packages
- [cutorch](https://github.com/torch/cutorch)
- [nn](https://github.com/torch/nn)
- [cunn](https://github.com/torch/cunn)
- [nngraph](https://github.com/torch/nngraph)
- [cudnn](https://github.com/soumith/cudnn.torch)
- [xlua](https://github.com/torch/xlua)
- [image](https://github.com/torch/image)
- [paths](https://github.com/torch/paths)
- [fb.python](https://github.com/facebook/fblualib/blob/master/fblualib/python/README.md)
Note: if you are having troubles compiling thpp (required for fb.python) against the latest version of torch7 please use the version available here: [https://github.com/1adrianb/thpp](https://github.com/1adrianb/thpp)
### Python packages
- [numpy](http://www.numpy.org/)
- [matplotlib](https://matplotlib.org/)
- [dlib](https://pypi.python.org/pypi/dlib) (required for face detection, if no bbox are provided)
Please note that dlib performs poorly for faces found in challenging poses or difficult lighting conditions and it's provided only as a simple demo. For optimal performance we recommend using other deeplearning based face detection methods.
## Setup
Clone the github repository and install all the dependencies mentiones above.
```bash
git clone https://github.com/1adrianb/2D-and-3D-face-alignment
cd 2D-and-3D-face-alignment
```
## Usage
In order to run the demo please download the required models available bellow and the associated data.
```bash
th main.lua
```
In order to see all the available options please run:
```bash
th main.lua --help
```
## Docker image
For convenience, a Dockerfile is provided to build images with cuda support and cudnn v5.1:
```bash
docker build -t facealignment .
```
Alternatively you can use the image available on [docker hub](https://hub.docker.com/r/1adrianb/facealignment-torch/):
```bash
nvidia-docker run -it 1adrianb/facealignment-torch
```
In order to keep the image small the data and the models are not included and will have to be downloaded separately.
Docker image based on the [cuda-torch](https://hub.docker.com/r/kaixhin/cuda-torch/) by kaixhin.
## Pretrained models
[2D-FAN](https://www.adrianbulat.com/downloads/FaceAlignment/2D-FAN-300W.t7) - trained on 300W-LP and finetuned on iBUG training set.
[3D-FAN](https://www.adrianbulat.com/downloads/FaceAlignment/3D-FAN.t7) - trained on 300W-LP
[2D-to-3D-FAN](https://www.adrianbulat.com/downloads/FaceAlignment/2D-to-3D-FAN.tar.gz) - trained on 300W-LP
[3D-FAN-depth](https://www.adrianbulat.com/downloads/FaceAlignment/3D-FAN-depth.t7) - trained on 300W-LP
## Citation
```
@inproceedings{bulat2017far,
title={How far are we from solving the 2D \& 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)},
author={Bulat, Adrian and Tzimiropoulos, Georgios},
booktitle={International Conference on Computer Vision},
year={2017}
}
```
## Dataset
You can download the annotations alongside the images used by visiting [our page](https://www.adrianbulat.com/face-alignment).