A Real-Time 3D Modeling System Using Multiple Stereo Cameras for Free-Viewpoint Video Generation

  • Hansung Kim
  • Itaru Kitahara
  • Kiyoshi Kogure
  • Kwanghoon Sohn
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4142)


We propose a real-time 3D modeling system using multiple stereo cameras which is a method for displaying a target object from an arbitrary view. Each capturing PC segments the objects and estimates disparity fields, then they transmit the data to a 3D modeling server. A modeling server generates 3D models of the objects and renders a video at the designated point of view. A main contribution in this system is a shape-recovery algorithm to derive a 3D scene description from 2D images. We propose an efficient volume carving algorithm using silhouette and disparity at a time that is more robust than conventional algorithms. The algorithm partitions space into an octree and processes it hierarchically so that execution time and space are dramatically reduced. The generated free-view video provides realistic images of dynamically changing scenes in real-time.


Video Stream Virtual View Visual Hull Foreground Region Disparity Estimation 
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.
    Izquierdo, E.M., Ohm, J.R.: Image-based Rendering and 3D Modeling: A Complete Framework. Signal Proc.: Image Communication 15, 817–858 (2000)CrossRefGoogle Scholar
  2. 2.
    Redert, P.A.: Multi-viewpoint Systems for 3-D Visual Communication. Ph.D. thesis, Delft University of Technology (2000)Google Scholar
  3. 3.
    Shapiro, L.G., Stockman, G.C.: Computer Vision, ch. 12. Prentice Hall, New Jersey (2001)Google Scholar
  4. 4.
    Matusik, W.: Image-Based Visual Hulls. MS Thesis. MIT (1997)Google Scholar
  5. 5.
    Matsuyama, T., Wu, X., Takai, T., Wada, T.: Real-Time Dynamic 3-D Object Shape Reconstruction and High-Fidelity Texture Mapping for 3-D Video. IEEE Trans. CSVT 14, 357–369 (2004)Google Scholar
  6. 6.
    Yemeza, Y., Schmitt, F.: 3D Reconstruction of Real Objects with High Resolution Shape and Texture. Image and Vision Computing 22, 1137–1153 (2004)CrossRefGoogle Scholar
  7. 7.
    Esteban, C.H., Schmitt, F.: Multi-Stereo 3D Object Reconstruction. In: Proc. 3DPVT, pp. 159–167 (2002)Google Scholar
  8. 8.
    Cheung, G.K.M., Baker, S., Kanade, T.: Visual Hull Alignment and Refinement Across Time: A 3D Reconstruction Algorithm Combining Shape-From-Silhouette with Stereo. In: Proc. CVPR, pp. 375–382 (2003)Google Scholar
  9. 9.
    Kim, H., Kitahara, I., Kogure, K., Hagita, N., Sohn, K.: Sat-Cam: Personal Satellite Virtual Camera. In: Aizawa, K., Nakamura, Y., Satoh, S. (eds.) PCM 2004. LNCS, vol. 3333, pp. 87–94. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  10. 10.
    Kim, H., Choe, Y., Sohn, K.: Disparity Estimation Using Region-dividing Technique with Energy-based Regularization. Optical Engineering 43, 1882–1890 (2004)CrossRefGoogle Scholar
  11. 11.
    Everitt, C.: Projective Texture Mapping. NVIDIA SDK White Paper (2001)Google Scholar
  12. 12.
  13. 13.
    Lorensen, W.E., Cline, H.E.: Marching Cubes: A High Resolution 3D Surface Construction Algorithm. In: SIGGRAPH 1987, vol. 21, pp. 163–169 (1987)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Hansung Kim
    • 1
    • 2
  • Itaru Kitahara
    • 1
  • Kiyoshi Kogure
    • 1
  • Kwanghoon Sohn
    • 2
  1. 1.Knowledge Science Lab, ATRKyotoJapan
  2. 2.Dept. of Electrical and Electronics Eng.Yonsei UniversitySeoulKorea

Personalised recommendations