SMPLicit

Implementation for the paper SMPLicit: Topology-aware Generative Model for Clothed People (CVPR 2021)

Installation

Follow these commands to install SMPLicit in your environment. The required libraries are standard, with the possible exception of Kaolin which requires a particular version to run with the current code.

  • git clone https://github.com/ecorona/SMPLicit
  • cd SMPLicit
  • Install the dependencies listed in requirements.txt:
    • pip install -r requirements.txt
  • In particular, we use Kaolin v0.1 (see installation command) which should be easy to install. However, if you want to use a later version, you might need to update the import to TriangleMesh in SMPLicit/SMPLicit.py
  • Download the SMPL model from here and place it in SMPLicit/utils/

To be able to import and use SMPLicit in another project, just use run python setup.py install in the main folder.

Usage

To check that everything is going well, run one of the test scripts under the examples folder. The first example will just show a simple T-Shirt on a standard shaped SMPL and visualize it using trimesh, to make sure everything is working.

cd examples/
python example.py

SMPLicit can represent clothes of different types, so the following example will also add lower-body clothes, hair and shoes into the example:

python example_fullbody.py

And finally one can interpolate between clothes of different types. For instance, moving between a jacket, tops, short or long sleeved T-Shirts. The following script will generate object meshes that represent these clothes and will be saved in interpolation/, below the main folder.

python interpolate.py

Citation

If you find the code useful, please cite:

@inproceedings{corona2021smplicit,
    Author = {Enric Corona and Albert Pumarola and Guillem Aleny{\`a} and Pons-Moll, Gerard and Moreno-Noguer, Francesc},
    Title = {SMPLicit: Topology-aware Generative Model for Clothed People},
    Year = {2021},
    booktitle = {CVPR},
}

GitHub

https://github.com/enriccorona/SMPLicit