3D Body Reconstruction from Photos Based on Range Scan

  • Hyewon Seo
  • Young In Yeo
  • Kwangyun Wohn
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3942)


We present a data-driven shape model for reconstructing human body models from one or more 2D photos. One of the key tasks in reconstructing the 3D model from image data is shape recovery, a task done until now in utterly geometric way, in the domain of human body modeling. In contrast, we adopt a data-driven, parameterized deformable model that is acquired from a collection of range scans of real human body. The key idea is to complement the image-based reconstruction method by leveraging the quality shape and statistic information accumulated from multiple shapes of range-scanned people. In the presence of ambiguity either from the noise or missing views, our technique has a bias towards representing as much as possible the previously acquired ‘knowledge’ on the shape geometry. Texture coordinates are then generated by projecting the modified deformable model onto the front and back images. Our technique has shown to reconstruct successfully human body models from minimum number images, even from a single image input.


Feature Point Shape Recovery Deformable Model Template Model Virtual Camera 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ahn, J.H., Sul, C.H., Park, E.K., Wohn, K.W.: Lan-based Optical Motion Capture System. In: Proc. Korea Conference on Human Computer Interaction 2000, pp. 429–432 (2000)Google Scholar
  2. 2.
    Allen, B., Curless, B., Popovic, Z.: The space of human body shapes: reconstruction and parameterization from range scans. In: Proc. SIGGRAPH 2003, pp. 587–594. Addison-Wesley, Reading (2003)CrossRefGoogle Scholar
  3. 3.
    Blanz, B., Vetter, T.: A morphable model for the synthesis of 3D faces. In: Proc. SIGGRAPH 1999, pp. 187–194. Addison-Wesley, Reading (1999)CrossRefGoogle Scholar
  4. 4.
    Cordier, F., Seo, H., Magnenat-Thalmann, N.: Made-to-Measure Technologies for Online Clothing Store. In: IEEE CG&A special issue on Web Graphics, pp. 38–48 (January 2003)Google Scholar
  5. 5.
    Hamamatsu BL scanner, http://www.hpk.co.jp
  6. 6.
    Hilton, A., Beresford, D., Gentils, T., Smith, R.J., Sun, W., Illingworth, J.: Whole-body modelling of people from multi-view images to populate virtual worlds. Visual Computer: International Journal of Computer Graphics 16(7), 411–436 (2000)MATHCrossRefGoogle Scholar
  7. 7.
    Lee, W., Gu, J., Magnenat-Thalmann, N.: Generating Animatable 3D Virtual Humans from Photographs. In: Computer Graphics Forum, Proc. Eurographics 2000 Interlaken, Switzerland, vol. 19(3), pp. 1–10 (August 2000)Google Scholar
  8. 8.
    Press, W.H., Flannery, B.P., Teukolsky, S.A., Vetterling, W.T.: Numerical Recipes in C. The art of scientific computing. Cambridge University Press, Cambridge (1988)Google Scholar
  9. 9.
    Sand, P., McMillan, L., Popovic, J.: Continuous Capture of Skin Deformation. In: Proc. ACM SIGGRAPH 2003, pp. 578–586 (2003)Google Scholar
  10. 10.
    Seo, H., Magnenat-Thalmann, N.: An Automatic Modeling of Human Bodies from Sizing Parameters. In: ACM SIGGRAPH Symposium on Interactive 3D Graphics, pp. 19–26. ACM Press, New York (2003)Google Scholar
  11. 11.
    Seo, H.: Parameterized Human Body Modeling. PhD thesis, Departement d’informatique, University of Geneva (2004)Google Scholar
  12. 12.
    Tsai, R.Y.: An Efficient and Accurate Camera Calibration Technique for 3D Machine Vision. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Miami Beach, FL, pp. 364–374 (1986)Google Scholar
  13. 13.
  14. 14.
    Telmat Industrie SA, http://www.telmat.com

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Hyewon Seo
    • 1
  • Young In Yeo
    • 2
  • Kwangyun Wohn
    • 2
  1. 1.CGALChungnam National UniversityDaejeonKorea
  2. 2.VRLab.KAISTDaejeonKorea

Personalised recommendations