By Jianzhu Guo, Xiangyu Zhu, Yang Yang, Fan Yang, Zhen Lei and Stan Z. Li.

This is an extended work of the github improved version of 3DDFA, named Towards Fast, Accurate and Stable 3D Dense Face Alignment, accepted by ECCV 2020. The supplementary material is here.

The PyTorch code and models will be released in next days. 😃

1. Clone this repo

git clone https://github.com/cleardusk/3DDFA_V2.git
cd 3DDFA_V2

2. Build Cython version of NMS

cd FaceBoxes
sh ./build_cpu_nms.sh

3. Run demos

# running on still image
python3 demo.py -f examples/inputs/emma.jpg

# running on videos
python3 demo_video.py -f examples/inputs/videos/214.avi

# running on videos smoothly by looking ahead by `n_next` frames
python3 demo_video_smooth.py -f examples/inputs/videos/214.avi

The implementation of tracking is simply by alignment. If the head pose > 90° or the motion is too fast, the alignment may fail. I use a threshold to trickly check the tracking state, but it is unstable.

You can refer to demo.ipynb for the step-by-step tutorial.

If your work or research benefits from this repo, please cite two bibs below : )

@inproceedings{guo2020towards,
    title =        {Towards Fast, Accurate and Stable 3D Dense Face Alignment},
    author =       {Guo, Jianzhu and Zhu, Xiangyu and Yang, Yang and Yang, Fan and Lei, Zhen and Li, Stan Z},
    booktitle =    {Proceedings of the European Conference on Computer Vision (ECCV)},
    year =         {2020}
}

@misc{3ddfa_cleardusk,
    author =       {Guo, Jianzhu and Zhu, Xiangyu and Lei, Zhen},
    title =        {3DDFA},
    howpublished = {\url{https://github.com/cleardusk/3DDFA}},
    year =         {2018}
}

Jianzhu Guo (郭建珠) [Homepage, Google Scholar]: [email protected] or [email protected].