A multi-view SMPL fitting based on smplify-x
conda install pytorch==1.1.0 torchvision==0.3.0 cudatoolkit=10.0 -c pytorch
pip install -r requirements.txt
Download the official SMPL model from SMPLify website (netural) and SMPL website (male/female). Then, rename the .pkl files and put them in the models/smpl folder. (see models/smpl/readme.txt)
Run python code/main.py --config cfg_files/fit_smpl.yaml
We add a collision term based on SDF. You need to install sdf and set interpenetration: true in the cfg_files/fit_smpl.yaml before using this code.
cd sdf
python setup.py install
@inproceedings{zhang2020object,
title={Object-Occluded Human Shape and Pose Estimation From a Single Color Image},
author={Zhang, Tianshu and Huang, Buzhen and Wang, Yangang},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={7376--7385},
year={2020}
}
@inproceedings{SMPL-X:2019,
title = {Expressive Body Capture: 3D Hands, Face, and Body from a Single Image},
author = {Pavlakos, Georgios and Choutas, Vasileios and Ghorbani, Nima and Bolkart, Timo and Osman, Ahmed A. A. and Tzionas, Dimitrios and Black, Michael J.},
booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
year = {2019}
}