multiview_optimization

Download pre-trained models and data from SMPLX and PIXIE projects.

For more information please follow PIXIE installation.

For multiview optimization you need to have the following files SMPL-X__FLAME_vertex_ids.npy, smplx_extra_joints.yaml, SMPLX_NEUTRAL_2020.npz and change a path to them in ./utils/config.py

Note, that you need to obtain PIXIE initialization for shape, pose parameters and save it as a dict in initialization_pixie file (see the structure in example scene for convenience).

Furthermore, use OpenPose to obtain 3d keypoints or use only FaceAlignment loss in optimization process.

To obtain FLAME prior run:

bash run_monocular_fitting.sh

To visualize the training process:

tensorboard --logdir ./experiments/EXP_NAME

After training put obtained FLAME prior mesh.obj into the dataset folder ./implicit-hair-data/data/SCENE_TYPE/CASE/head_prior.obj.