FacePoseNet: Making a Case for Landmark-Free Face Alignment

Abstract

We show how a simple convolutional neural network (CNN) can be trained to accurately and robustly regress 6 degrees of freedom (6DoF) 3D head pose, directly from image intensities. We further explain how this FacePoseNet (FPN) can be used to align faces in 2D and 3D as an alternative to explicit facial landmark detection for these tasks. We claim that in many cases the standard means of measuring landmark detector accuracy can be misleading when comparing different face alignments. Instead, we compare our FPN with existing methods by evaluating how they affect face recognition accuracy on the IJB-A and IJB-B benchmarks: using the same recognition pipeline, but varying the face alignment method. Our results show that (a) better landmark detection accuracy measured on the 300W benchmark does not necessarily imply better face recognition accuracy. (b) Our FPN provides superior 2D and 3D face alignment on both benchmarks. Finally, (c), FPN aligns faces at a small fraction of the computational cost of comparably accurate landmark detectors. For many purposes, FPN is thus a far faster and far more accurate face alignment method than using facial landmark detectors.

References in corpus (10)

• Deep Residual Learning for Image Recognition
• Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition
• Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
• Deep Learning Face Attributes in the Wild
• Do We Really Need to Collect Millions of Faces for Effective Face Recognition?
• Facial Landmark Detection with Tweaked Convolutional Neural Networks
• An All-In-One Convolutional Neural Network for Face Analysis
• Single View Depth Estimation from Examples
• A Multi-Scale Cascade Fully Convolutional Network Face Detector
• Learning Detailed Face Reconstruction from a Single Image

Cited by in corpus (5)

• Pairwise Relational Networks for Face Recognition
• ExpNet: Landmark-Free, Deep, 3D Facial Expressions
• MultiFace: A Generic Training Mechanism for Boosting Face Recognition Performance
• A Fast and Accurate System for Face Detection, Identification, and Verification
• Statistical transformer networks: learning shape and appearance models via self supervision