Real-Time 4D Reconstruction of Human Motion

  • József Hapák
  • Zsolt Jankó
  • Dmitry Chetverikov
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7378)


A studio for real-time 4D reconstruction of moving actors and deformable objects has been recently created at the Computer and Automation Research Institute of the Hungarian Academy of Sciences (MTA SZTAKI). The studio uses 13 synchronised, calibrated high-resolution video cameras and a GPU to build dynamic 3D models providing free-viewpoint video in real-time. We give a brief overview of advanced studios operating around the world, then discuss the GPU implementation details of the reconstruction pipeline. Finally, a performance comparison of the offline and real-time versions of the system is given.


Visual Hull Volumetric Model Skeleton Model Marching Cube Texture Atlas 
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.
    Carranza, J., Theobalt, C., Magnor, M., Seidel, H.: Free-viewpoint video of human actors. ACM Transactions on Graphics 22, 569–577 (2003)CrossRefGoogle Scholar
  2. 2.
    FORTH ICS: From multiple views to textured 3D meshes: a GPU-powered approach (2010),
  3. 3.
    INRIA Rhône-Alpes: The Grid and Image Initiative (2012),
  4. 4.
    Jankó, Z., Chetverikov, D., Hapák, J.: 4D Reconstruction Studio: Creating dynamic 3D models of moving actors. In: Proc. Sixth Hungarian Conference on Computer Graphics and Geometry, pp. 1–7 (2012),
  5. 5.
    Janko, Z., Pons, J.P.: Spatio-temporal image-based texture atlases for dynamic 3-D models. In: Proc. ICCV Workshop 3DIM 2009, pp. 1646–1653 (2009)Google Scholar
  6. 6.
    Kutulakos, K., Seitz, S.: A theory of shape by space carving. In: Proc. International Conference on Computer Vision, vol. 1, pp. 307–314 (1999)Google Scholar
  7. 7.
    Laurentini, A.: The visual hull concept for silhouette-based image understanding. IEEE Trans. Pattern Analysis and Machine Intelligence 16, 150–162 (1994)CrossRefGoogle Scholar
  8. 8.
    Lorensen, W., Cline, H.: Marching cubes: A high resolution 3D surface construction algorithm. In: Proc. ACM SIGGRAPH, vol. 21, pp. 163–169 (1987)Google Scholar
  9. 9.
    MIT CGP: Dynamic Shape Capture and Articulated Shape Animation (2011),
  10. 10.
    Morpheo Team: Capture and Analysis of Shapes in Motion (2012),
  11. 11.
    MPI Informatik: Dynamic Scene Reconstruction (2012),
  12. 12.
    University of Surrey: SurfCap: Surface Motion Capture (2008),
  13. 13.
    Zhang, R., Tsai, P., Cryer, J., Shah, M.: Shape-from-shading: a survey. IEEE Trans. Pattern Analysis and Machine Intelligence 21, 690–706 (1999)CrossRefGoogle Scholar
  14. 14.
    Zhang, Z.: A flexible new technique for camera calibration. IEEE Trans. Pattern Analysis and Machine Intelligence 22, 1330–1334 (2000)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • József Hapák
    • 1
  • Zsolt Jankó
    • 1
  • Dmitry Chetverikov
    • 1
  1. 1.MTA SZTAKI and Eötvös Loránd UniveristyBudapestHungary

Personalised recommendations