High-Fidelity Pose and Expression Normalization for Face Recognition in the Wild
Xiangyu Zhu Zhen Lei Junjie Yan Dong Yi Stan Z. Li
Pose and expression normalization is a crucial step to recover the canonical view of faces under arbitrary conditions, so as to improve the face recognition performance. An ideal normalization method is desired to be automatic, database independent and high-fidelity, where the face appearance should be preserved with little artifact and information loss. However, most normalization methods fail to satisfy one or more of the goals. We propose a High-fidelity Pose and Expression Normalization (HPEN) method with 3D Morphable Model (3DMM) which can automatically generate a natural face image in frontal pose and neutral expression. The following paper describes our algorithm.
Xiangyu Zhu, Zhen Lei, Junjie Yan, Dong Yi, Stan Z. Li, “High-Fidelity Pose and Expression Normalization for Face Recognition in the Wild”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
Updates:
l [new] Extracting the “Pose Adaptive 3DMM Fitting” part in HPEN for downloading.
Downloads:
1. [HPEN]: We release the MATLAB implementation of High-fidelity Pose and Expression Normalization. Please read the readme.txt for how to install and run the code. Note that the Basel Face Model is necessary for this implementation and you may need to apply for that before using.
2. [LFW_HPEN]: The normalization results of the
LFW database are also released. For each sample, the normalization result and
the 68-landmarks makeup are provided.
3. [MultiPIE_HPEN]: The normalization results
of the MultiPIE database including setting-1 and setting-2.
4. [3DMM Fitting]: We release the “Pose Adaptive 3DMM
fitting” part of HPEN since it is very useful in 3DMM applications.