FacePoseNet: Making a Case for Landmark-Free Face Alignment

24 Aug 2017  ·  Feng-Ju Chang, Anh Tuan Tran, Tal Hassner, Iacopo Masi, Ram Nevatia, Gerard Medioni ·

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.

PDF Abstract

Results from the Paper

 Ranked #1 on Facial Landmark Detection on 300W (Mean Error Rate metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Facial Landmark Detection 300W FPN Mean Error Rate 0.1043 # 1
Face Verification IJB-A FPN TAR @ FAR=0.01 90.1% # 10
Face Identification IJB-A FPN Accuracy 91.4% # 2
Face Verification IJB-B FPN TAR @ FAR=0.01 96.5% # 5
Face Identification IJB-B FPN Accuracy 91.1% # 1


No methods listed for this paper. Add relevant methods here