This project is an implementation for "Led3D: An lightweight and efficent deep approach to recognizing low-quality 3d faces" [ Download ], which is accepted by CVPR2019.
Dataset: Lock3DFace
Lable: Lock3DFace Label File
- 3D Face Preprocessing (Done.)
- 3D Face Augmentation (Done.)
- Python Inference Code (Done.)
@InProceedings{Mu_2019_CVPR,
author = {Mu, Guodong and Huang, Di and Hu, Guosheng and Sun, Jia and Wang, Yunhong},
title = {Led3D: A Lightweight and Efficient Deep Approach to Recognizing Low-Quality 3D Faces},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}