A Synthesis Method for Personalized 3D Face Reconstruction

  • Yu-chen Yan
  • Hai-bin Liao
  • Qing-hu Chen
  • Cheng-Yi Xiong
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 217)


In order to balance modeling time and modeling accuracy of 3D face reconstruction, in this paper, we propose an integrated modeling approach combining shape-from-shading (SFS) and local morphable model (LMM), which can rapidly create a realistic 3D face model on the basis of a single 2D image. This method obtains 3D face (which is called 3D contour face) quickly by SFS firstly; then, recovers local accurate 3D data by LMM; lastly, reconstructs a 3D face model of high accuracy by carrying out interpolation smoothing on the 3D contour face with local 3D accurate data. Experimental results show that the method has the advantages of modeling with higher accuracy and lower complexity, and can reconstruct personalized 3D face model from a single real-world photo in a short time.


3D face modeling Shape-from-shading 3D morphable model Radial basis function interpolation 


  1. 1.
    Zha HB, Wang P (2003) Realistic face modeling by registration of 3D meshes models and multi-view color images. In: Proceedings of the 8th International Conference Computer Aided Design and Computer Graphics. Macao: Welfare Printing Limited 3(3):217–222Google Scholar
  2. 2.
    DeCarlo D, Metaxas D, Stone M (1998) An anthropometric face model using variational techniques. In: Proceedings of the 25th annual conference on Computer graphics and interactive techniques, New York: SIGGRA 2(12):67–74Google Scholar
  3. 3.
    Liu Z, Zhang Z, Jacobs C et al (2000) Rapid modeling of animated faces from video. Technical Report MSR-TR-2000-11, Microsoft Research, Microsoft Corporation 23(1):1–8Google Scholar
  4. 4.
    Kemelmacher I, Basri R (2006) Molding face shapes by example//Proceedings of the ECCV 23(5):277–288Google Scholar
  5. 5.
    Castelan M, Hancock ER (2006) Acquiring height data from a single image of a face using local shape indicators. Comput Vis Image Underst 103(1):64–79CrossRefGoogle Scholar
  6. 6.
    Smith WAP, Hancock ER (2006) Recovering facial shape and albedo using a statistical model of surface normal direction. IEEE Trans Pattern Anal Mach Intell 28(12):1914–1930CrossRefGoogle Scholar
  7. 7.
    Blanz V, Vetter T (2003) Face recognition based on fitting a 3D morphable model. IEEE Trans Pattern Anal Mach Intell 25(9):1063–1074CrossRefGoogle Scholar
  8. 8.
    Zhou S, Chellappa R, Jacobs D (2004) Characterization of human faces under illumination variations using rank, integrability, and symmetry constraints. In: Proceedings of the ECCV 7(4):588–601Google Scholar
  9. 9.
    Smith W, Hancock E (2005) Recovering facial shape and albedo using a statistical model of surface normal direction. In: Proceedings of the ICCV 3(5):588–595Google Scholar
  10. 10.
    Samaras D, Metaxas D, Fua P, Leclerc Y (2000) Variable albedo surface reconstruction from stereo and shape from shading. In: IEEE conference on computer vision and pattern recognition, Hilton Head Island, SC, USA 45(4):480–487Google Scholar
  11. 11.
    Wallraven C, Blanz V, Vetten T (1999) 3D-reconstruction of faces: combining stereo with class-based knowledge. In: DAGM-Symposium 2(3):405–412Google Scholar
  12. 12.
    Zheng Q, Chellappa R (1991) Estimation of Illuminant Direction, Albedo, and Shape from Shading. IEEE Trans Pattern Anal Mach Intell 13(7):680–702CrossRefGoogle Scholar
  13. 13.
    Brooks MJ, Horn BKP (1985) Shape and source from shading. In: Proceedings of International Joint Conference Artificial Intelligence 23(2):932–936Google Scholar
  14. 14.
    Limhfe T (2005) BJUT-3D the BJUT-3D large-scale Chinese face database. MISKL-TR-05-FMFR-001, multimedia and intelligent software technology Beijing municipal key laboratory, Beijing University of Technology 26(2):12–19Google Scholar
  15. 15.
    Blanz V, Vetter T (2002) Reconstructing the complete 3D shape of faces from partial information. Informationstechnik and Technische Informatik 44(6):295–302Google Scholar
  16. 16.
    Baek S-Y, Kim BY, Lee K (2009) 3D face model reconstruction from single 2D frontal image. In: Proceedings Of the 8th international conference on virtual reality continuum and its applications in industry, New York, USA 12(3):15–19Google Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  • Yu-chen Yan
    • 1
  • Hai-bin Liao
    • 1
    • 2
  • Qing-hu Chen
    • 1
  • Cheng-Yi Xiong
    • 2
  1. 1.School of Electronic InformationWuhan University, WuhanWuhanChina
  2. 2.College of Electronic Information Engineering, Hubei Key Lab of Intelligent Wireless CommunicationSouth-Central University for NationalitiesWuhanChina

Personalised recommendations