godspeed1989 / coma

Convolutional Mesh Autoencoders for Generating 3D Faces

CoMA: Convolutional Mesh Autoencoders

This is an official repository of Generating 3D Faces using Convolutional Mesh Autoencoders

[Project Page][Arxiv]

Requirements

This code is tested on Tensorflow 1.3. Requirements (including tensorflow) can be installed using:

pip install -r requirements.txt

Install mesh processing libraries from MPI-IS/mesh.

Data

Download the data from the Project Page.

Preprocess the data

python processData.py --data <PATH_OF_RAW_DATA> --save_path <PATH_TO_SAVE_PROCESSED DATA>

Data pre-processing creates numpy files for the interpolation experiment and extrapolation experiment (Section X of the paper). This creates 13 different train and test files. sliced_[train|test] is for the interpolation experiment. <EXPRESSION>_[train|test] are for cross validation cross 12 different expression sequences.

Training

To train, specify a name, and choose a particular train test split. For example,

python main.py --data data/sliced --name sliced

Testing

To test, specify a name, and data. For example,

python main.py --data data/sliced --name sliced --mode test

Acknowledgements

We thank Raffi Enficiaud and Ahmed Osman for pushing the release of psbody.mesh, an essential dependency for this project.

License

The code contained in this repository is under MIT License and is free for commercial and non-commercial purposes. The dependencies, in particular, MPI-IS/mesh and our data have their own license terms which can be found on their respective webpages. The dependencies and data are NOT covered by MIT License associated with this repository.

When using this code, please cite

Ranjan, Anurag, Timo Bolkart, Soubhik Sanyal, and Michael J. Black. "Generating 3D faces using Convolutional Mesh Autoencoders." ECCV 2018.