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.
|Title of host publication||Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||10|
|State||Published - 1 Jul 2017|
|Event||16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017 - Venice, Italy|
Duration: 22 Oct 2017 → 29 Oct 2017
|Name||Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017|
|Conference||16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017|
|Period||22/10/17 → 29/10/17|
Bibliographical noteFunding Information:
This research is based upon work supported in part by theOffice oftheDirectorofNationalIntelligence(ODNI), IntelligenceAdvanced ResearchProjectsActivity (IARPA), viaIARPA2014-14071600011. Theviews andconclusions containedhereinarethoseoftheauthorsandshouldnot be interpretedas necessarilyrepresenting theofficial poli-ciesorendorsements, eitherexpressedorimplied, ofODNI, IARPA, ortheU.S.Government. TheU.S.Governmentis authorizedtoreproduceanddistribute reprintsforGovern-mental purpose notwithstanding any copyright annotation thereon.
This research is based upon work supported in part by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via IARPA 2014-14071600011. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of ODNI, IARPA, or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Governmental purpose notwithstanding any copyright annotation thereon.