Unconstrained Face Alignment via Cascaded Compositional Learning

We present a practical approach to address the problem of unconstrained face alignment for a single image. In our unconstrained problem, we need to deal with large shape and appearance variations under extreme head poses and rich shape deformation. To equip cascaded regressors with the capability to handle global shape variation and irregular appearance-shape relation in the unconstrained scenario, we partition the optimisation space into multiple domains of homogeneous descent, and predict a shape as a composition of estimations from multiple domain-specific regressors. With a specially formulated learning objective and a novel tree splitting function, our approach is capable of estimating a robust and meaningful composition. In addition to achieving state-of-the-art accuracy over existing approaches, our framework is also an efficient solution (350 FPS), thanks to the on-the-fly domain exclusion mechanism and the capability of leveraging the fast pixel feature.

[1]  Hyeonjoon Moon,et al.  The FERET Evaluation Methodology for Face-Recognition Algorithms , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Georgios Tzimiropoulos,et al.  Project-Out Cascaded Regression with an application to face alignment , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Cheng Li,et al.  Face alignment by coarse-to-fine shape searching , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Peter Robinson,et al.  Face Alignment Assisted by Head Pose Estimation , 2015, BMVC.

[5]  Qiang Ji,et al.  Robust Facial Landmark Detection Under Significant Head Poses and Occlusion , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[6]  Claudia Lindner,et al.  Robust and Accurate Shape Model Matching Using Random Forest Regression-Voting. , 2015, IEEE transactions on pattern analysis and machine intelligence.

[7]  Wenhan Luo,et al.  Unified Face Analysis by Iterative Multi-output Random Forests , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Ira Kemelmacher-Shlizerman,et al.  MegaFace: A Million Faces for Recognition at Scale , 2015, ArXiv.

[9]  Pietro Perona,et al.  Cascaded pose regression , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  Stefanos Zafeiriou,et al.  The First Facial Landmark Tracking in-the-Wild Challenge: Benchmark and Results , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[11]  Hyeonjoon Moon,et al.  The FERET evaluation methodology for face-recognition algorithms , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Ioannis Patras,et al.  Sieving Regression Forest Votes for Facial Feature Detection in the Wild , 2013, 2013 IEEE International Conference on Computer Vision.

[13]  Donghoon Lee,et al.  Fast and Accurate Head Pose Estimation via Random Projection Forests , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[14]  Rama Chellappa,et al.  Growing Regression Forests by Classification: Applications to Object Pose Estimation , 2013, ECCV.

[15]  Takeo Kanade,et al.  Multi-PIE , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[16]  Jian Sun,et al.  Face Alignment by Explicit Shape Regression , 2012, International Journal of Computer Vision.

[17]  Ashraf A. Kassim,et al.  Facial Landmark Detection via Progressive Initialization , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[18]  Juergen Gall,et al.  Class-specific Hough forests for object detection , 2009, CVPR.

[19]  Deva Ramanan,et al.  Face detection, pose estimation, and landmark localization in the wild , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Xiaoming Liu,et al.  Pose-Invariant 3D Face Alignment , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[22]  Jian Sun,et al.  Face Alignment at 3000 FPS via Regressing Local Binary Features , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Horst Bischof,et al.  Annotated Facial Landmarks in the Wild: A large-scale, real-world database for facial landmark localization , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[24]  Nicu Sebe,et al.  Regressing a 3D Face Shape from a Single Image , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[25]  Ankur Datta,et al.  Hierarchical ranking of facial attributes , 2011, Face and Gesture 2011.

[26]  Ying Wu,et al.  Detecting and Aligning Faces by Image Retrieval , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Donghoon Lee,et al.  Face alignment using cascade Gaussian process regression trees , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Jian Sun,et al.  Joint Cascade Face Detection and Alignment , 2014, ECCV.

[29]  Fernando De la Torre,et al.  Global supervised descent method , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  J. Crowley,et al.  Estimating Face orientation from Robust Detection of Salient Facial Structures , 2004 .

[31]  Pietro Perona,et al.  Robust Face Landmark Estimation under Occlusion , 2013, 2013 IEEE International Conference on Computer Vision.

[32]  Stefanos Zafeiriou,et al.  Unifying holistic and Parts-Based Deformable Model fitting , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[34]  Junzhou Huang,et al.  Pose-Free Facial Landmark Fitting via Optimized Part Mixtures and Cascaded Deformable Shape Model , 2013, 2013 IEEE International Conference on Computer Vision.

[35]  Xiaogang Wang,et al.  Deep Convolutional Network Cascade for Facial Point Detection , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[36]  Stefanos Zafeiriou,et al.  300 Faces in-the-Wild Challenge: The First Facial Landmark Localization Challenge , 2013, 2013 IEEE International Conference on Computer Vision Workshops.

[37]  Stefanos Zafeiriou,et al.  A Comprehensive Performance Evaluation of Deformable Face Tracking “In-the-Wild” , 2016, International Journal of Computer Vision.

[38]  Shih-Chieh Huang,et al.  Regressive Tree Structured Model for Facial Landmark Localization , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[39]  Yu Yang,et al.  PIEFA: Personalized Incremental and Ensemble Face Alignment , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[40]  Hanjiang Lai,et al.  Deep Cascaded Regression for Face Alignment , 2015 .

[41]  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.

[42]  Josephine Sullivan,et al.  One millisecond face alignment with an ensemble of regression trees , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[43]  David J. Kriegman,et al.  Localizing parts of faces using a consensus of exemplars , 2011, CVPR.

[44]  Xiaoou Tang,et al.  Facial Landmark Detection by Deep Multi-task Learning , 2014, ECCV.

[45]  Dimitris N. Metaxas,et al.  Consensus of Regression for Occlusion-Robust Facial Feature Localization , 2014, ECCV.

[46]  Tal Hassner,et al.  Effective face frontalization in unconstrained images , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).