Deep 3D Portrait from a Single Image
This is a tensorflow implementation of the following paper: Deep 3d Portrait from a Single Image. We propose a two-step geometry learning scheme which first learn 3DMM face reconstruction from single images then learn to estimate hair and ear depth in a stereo setup.
git clone https://github.com/sicxu/Deep3dPortrait.git
cd Deep3dPortrait
pip install -r requirements.txtpython step1_recon_3d_face.py
python step2_face_segmentation.py
python step3_get_head_geometry.py
python step4_save_obj.pyIf you find this code helpful for your research, please cite our paper.
No open issues yet, or sync has not completed.