Effective face frontalization in unconstrained images

“Frontalization” is the process of synthesizing frontal facing views of faces appearing in single unconstrained photos. Recent reports have suggested that this process may substantially boost the performance of face recognition systems. This, by transforming the challenging problem of recognizing faces viewed from unconstrained viewpoints to the easier problem of recognizing faces in constrained, forward facing poses. Previous frontalization methods did this by attempting to approximate 3D facial shapes for each query image. We observe that 3D face shape estimation from unconstrained photos may be a harder problem than frontalization and can potentially introduce facial misalignments. Instead, we explore the simpler approach of using a single, unmodified, 3D surface as an approximation to the shape of all input faces. We show that this leads to a straightforward, efficient and easy to implement method for frontalization. More importantly, it produces aesthetic new frontal views and is surprisingly effective when used for face recognition and gender estimation.

[1]  Xiaoou Tang,et al.  Surpassing Human-Level Face Verification Performance on LFW with GaussianFace , 2014, AAAI.

[2]  Xiaogang Wang,et al.  Recover Canonical-View Faces in the Wild with Deep Neural Networks , 2014, ArXiv.

[3]  Tal Hassner,et al.  When standard RANSAC is not enough: cross-media visual matching with hypothesis relevancy , 2013, Machine Vision and Applications.

[4]  Kiriakos N. Kutulakos,et al.  A Theory of Shape by Space Carving , 2000, International Journal of Computer Vision.

[5]  Yuxiao Hu,et al.  Real-time conversion from a single 2D face image to a 3D text-driven emotive audio-visual avatar , 2008, 2008 IEEE International Conference on Multimedia and Expo.

[6]  Erik Learned-Miller,et al.  Labeled Faces in the Wild : Updates and New Reporting Procedures , 2014 .

[7]  Andrew Zisserman,et al.  Fisher Vector Faces in the Wild , 2013, BMVC.

[8]  Fei Yang,et al.  Expression flow for 3D-aware face component transfer , 2011, ACM Trans. Graph..

[9]  Fernando De la Torre,et al.  Supervised Descent Method and Its Applications to Face Alignment , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[11]  Hans-Peter Seidel,et al.  Exchanging Faces in Images , 2004, Comput. Graph. Forum.

[12]  Ming Yang,et al.  DeepFace: Closing the Gap to Human-Level Performance in Face Verification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Simon Lucey,et al.  Real-time avatar animation from a single image , 2011, Face and Gesture 2011.

[14]  Ira Kemelmacher-Shlizerman,et al.  Face Reconstruction from a Single Image using a Single Reference Face Shape , 2009 .

[15]  L. Whitaker.  Anthropometry of the Head and Face in Medicine. , 1983 .

[16]  Tal Hassner,et al.  Effective Unconstrained Face Recognition by Combining Multiple Descriptors and Learned Background Statistics , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Matti Pietikäinen,et al.  A Generalized Local Binary Pattern Operator for Multiresolution Gray Scale and Rotation Invariant Texture Classification , 2001, ICAPR.

[18]  Marwan Mattar,et al.  Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments , 2008 .

[19]  Xiaogang Wang,et al.  Deep Learning Face Representation by Joint Identification-Verification , 2014, NIPS.

[20]  Xiaogang Wang,et al.  Deep Learning Face Representation from Predicting 10,000 Classes , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Long Quan,et al.  Progressive surface reconstruction from images using a local prior , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[22]  Xiaogang Wang,et al.  Hybrid Deep Learning for Face Verification , 2013, 2013 IEEE International Conference on Computer Vision.

[23]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[24]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[25]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Peng Li,et al.  Similarity Metric Learning for Face Recognition , 2013, 2013 IEEE International Conference on Computer Vision.

[27]  Erik G. Learned-Miller,et al.  Unsupervised Joint Alignment of Complex Images , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[28]  R. Basri,et al.  Statistical Symmetric Shape from Shading for 3D Structure Recovery of Faces , 2004, eccv 2004.

[29]  Tal Hassner,et al.  Similarity Scores Based on Background Samples , 2009, ACCV.

[30]  Kun Zhou,et al.  Displaced dynamic expression regression for real-time facial tracking and animation , 2014, ACM Trans. Graph..

[31]  Tal Hassner,et al.  Viewing Real-World Faces in 3D , 2013, 2013 IEEE International Conference on Computer Vision.

[32]  Thomas Vetter,et al.  A morphable model for the synthesis of 3D faces , 1999, SIGGRAPH.

[33]  Yaniv Taigman,et al.  Descriptor Based Methods in the Wild , 2008 .

[34]  Alice J. O'Toole,et al.  FRVT 2006 and ICE 2006 large-scale results , 2007 .

[35]  Tal Hassner,et al.  The One-Shot similarity kernel , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[36]  Matthew Turk,et al.  A Morphable Model For The Synthesis Of 3D Faces , 1999, SIGGRAPH.

[37]  Daniel González-Jiménez,et al.  Symmetry-Aided Frontal View Synthesis for Pose-Robust Face Recognition , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[38]  Jiwen Lu,et al.  Discriminative Deep Metric Learning for Face Verification in the Wild , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[39]  Honglak Lee,et al.  Learning to Align from Scratch , 2012, NIPS.

[40]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[41]  Tal Hassner,et al.  Age and Gender Estimation of Unfiltered Faces , 2014, IEEE Transactions on Information Forensics and Security.