How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)
This is the training code for 2D-FAN and 3D-FAN decribed 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 webpage or read bellow for instructions on how to run the code.
Pretrained models are available on our page.
Demo code: https://www.github.com/1adrianb/2D-and-3D-face-alignment
Note: If you are interested in a binarized version, capable of running on devices with limited resources please also check https://github.com/1adrianb/binary-face-alignment for a demo.
- Clone the github repository and install all the dependencies mentiones above.
git clone https://github.com/1adrianb/face-alignment-training
cd face-alignment-training-
Download the 300W-LP dataset from the authors webpage. In order to train on your own data the dataloader.lua file needs to be adapted.
-
Download the 300W-LP annotations converted to t7 format from here, extract it and move the
landmarksfolder to the root of the 300W-LP dataset.
In order to run the demo please download the required models available bellow and the associated data.
th main.lua -data path_to_300W_LP_datasetIn order to see all the available options please run:
th main.lua --help@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}
}
This pipeline is build around the ImageNet training code avaialable at https://github.com/facebook/fb.resnet.torch and HourGlass(HG) code available at https://github.com/anewell/pose-hg-train