[Updates]

• 2018.10.4: Add Matlab face mesh rendering demo in visualize.
• 2018.9.9: Add pre-process of face cropping in benchmark.

This repo holds the pytorch implementation of paper Face Alignment in Full Pose Range: A 3D Total Solution. It releases the pre-trained first-stage pytorch models of MobileNet-V1 structure, the training dataset and code. The inference time is about 0.27ms per image on GeForce GTX TITAN X. More features will be added in future.

Several results (inferenced from model phase1_wpdc_vdc.pth.tar) are shown below.

@article{zhu2017face,
  title={Face Alignment in Full Pose Range: A 3D Total Solution},
  author={Zhu, Xiangyu and Lei, Zhen and Li, Stan Z and others},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2017},
  publisher={IEEE}
}

• PyTorch >= 0.4.0
• Python3.6

I strongly recommend using Python3.6 instead of older version for its better design.

When batch size is 128, the inference time of MobileNet-V1 takes about 34.7ms. The average speed is about 0.27ms/pic.

First, you should download the cropped testset ALFW and ALFW-2000-3D in test.data.zip, then unzip it and put it in the root directory. Next, run the benchmark code by providing trained model path. I have already provided four pre-trained models in models directory. These models are trained using different loss in the first stage. The model size is about 13M due to the high efficiency of MobileNet-V1 structure.

python3 ./benchmark.py -c models/phase1_wpdc_vdc.pth.tar

The performances of pre-trained models are shown below. In the first stage, the effectiveness of different loss is in order: WPDC > VDC > PDC. While the strategy using VDC to finetune WPDC achieves the best result.

The training scripts lie in training directory. The related resources are in below table.

After preparing the training dataset and configuration files, go into training directory and run the bash scripts to train. The training parameters are all presented in bash scripts.

Thanks for Xiangyu Zhu's great work. Thanks for your interest in this repo. If your research benefits from this repo, please cite it and star it 😃