Benchmarking 3D Pose Estimation for Face Recognition

3D-Model-Aided 2D face recognition (MaFR) has attracted a lot of attention in recent years. By registering a 3D model, facial textures of the gallery and the probe can be lifted and aligned in a common space, thus alleviating the challenge of pose variations. One obstacle preventing accurate registration is the 3D-2D pose estimation, which is easily affected by landmarks. In this work, we present the performance that state-of-the-art pose estimation algorithms could reach using state-of-the-art automatic landmark localization methods. We generated an application-specific dataset with more than 59,000 synthetic face images and ground truth camera pose and landmarks, covering 45 poses and six illumination conditions. Our experiments compared four recently proposed pose estimation algorithms using 2D landmarks detected by two automatic methods. Our results highlight one near-real-time landmark detection method and a highly accurate pose estimation algorithm, which would potentially boost the 3D-Model-Aided 2D face recognition performance.

[1]  Ioannis A. Kakadiaris,et al.  Bidirectional relighting for 3D-aided 2D face recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[3]  Stan Z. Li,et al.  Towards Pose Robust Face Recognition , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

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

[5]  Ioannis A. Kakadiaris,et al.  UHDB11 Database for 3D-2D Face Recognition , 2013, PSIVT.

[6]  V. Lepetit,et al.  EPnP: An Accurate O(n) Solution to the PnP Problem , 2009, International Journal of Computer Vision.

[7]  C. Taylor,et al.  Active shape models - 'Smart Snakes'. , 1992 .

[8]  Anil K. Jain,et al.  Deformation Modeling for Robust 3D Face Matching , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Yubin Kuang,et al.  Revisiting the PnP Problem: A Fast, General and Optimal Solution , 2013, 2013 IEEE International Conference on Computer Vision.

[10]  Ioannis A. Kakadiaris,et al.  Three-Dimensional Face Recognition in the Presence of Facial Expressions: An Annotated Deformable Model Approach , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Shiqi Li,et al.  A Stable Direct Solution of Perspective-Three-Point Problem , 2011, Int. J. Pattern Recognit. Artif. Intell..

[12]  Shiqi Li,et al.  A Robust O(n) Solution to the Perspective-n-Point Problem , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Stephen Milborrow.  Locating Facial Features with Active Shape Models , 2007 .

[14]  Gregory D. Hager,et al.  Fast and Globally Convergent Pose Estimation from Video Images , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  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.

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

[17]  Gee-Sern Hsu,et al.  Face Recognition across Poses Using a Single 3D Reference Model , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[18]  Ira Kemelmacher-Shlizerman,et al.  Ieee Transactions on Pattern Analysis and Machine Intelligence 1 3d Face Reconstruction from a Single Image Using a Single Reference Face Shape , 2022 .

[19]  Jim Graham,et al.  Robust Active Shape Model Search , 2002, ECCV.

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