Robust and Efficient Photo-Consistency Estimation for Volumetric 3D Reconstruction

  • Alexander Hornung
  • Leif Kobbelt
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3952)


Estimating photo-consistency is one of the most important ingredients for any 3D stereo reconstruction technique that is based on a volumetric scene representation. This paper presents a new, illumination invariant photo-consistency measure for high quality, volumetric 3D reconstruction from calibrated images. In contrast to current standard methods such as normalized cross-correlation it supports unconstrained camera setups and non-planar surface approximations. We show how this measure can be embedded into a highly efficient, completely hardware accelerated volumetric reconstruction pipeline by exploiting current graphics processors. We provide examples of high quality reconstructions with computation times of only a few seconds to minutes, even for large numbers of cameras and high volumetric resolutions.


Image Patch Visual Hull View Synthesis Neighboring Voxels Texture Size 
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.
    Seitz, S.M., Dyer, C.R.: Photorealistic scene reconstruction by voxel coloring. In: CVPR, pp. 1067–1073 (1997)Google Scholar
  2. 2.
    Kutulakos, K.N., Seitz, S.M.: A theory of shape by space carving. International Journal of Computer Vision 38, 199–218 (2000)CrossRefMATHGoogle Scholar
  3. 3.
    Esteban, C.H.: Stereo and Silhouette Fusion for 3D Object Modeling from Uncalibrated Images Under Circular Motion. PhD thesis, Ecole Nationale Supérieure des Télécommunications (2004)Google Scholar
  4. 4.
    Vogiatzis, G., Torr, P., Cipolla, R.: Multi-view stereo via volumetric graph-cuts. In: CVPR, pp. 391–398 (2005)Google Scholar
  5. 5.
    Sinha, S., Pollefeys, M.: Multi-view reconstruction using photo-consistency and exact silhouette constraints: A maximum-flow formulation. In: ICCV (2005)Google Scholar
  6. 6.
    Slabaugh, G.G., Schafer, R.W., Hans, M.C.: Image-based photo hulls for fast and photo-realistic new view synthesis. Real-Time Imaging 9, 347–360 (2003)CrossRefGoogle Scholar
  7. 7.
    Li, M., Magnor, M., Seidel, H.P.: Hardware-accelerated rendering of photo hulls. Computer Graphics Forum 23, 635–642 (2004)CrossRefGoogle Scholar
  8. 8.
    Bonet, J.S.D., Viola, P.A.: Roxels: Responsibility weighted 3D volume reconstruction. In: ICCV, pp. 418–425 (1999)Google Scholar
  9. 9.
    Zýka, V., Sára, R.: Polynocular image set consistency for local model verification. In: Workshop of the Austrian Association for Pattern Recognition, pp. 81–88 (2000)Google Scholar
  10. 10.
    Broadhurst, A., Drummond, T., Cipolla, R.: A probabilistic framework for space carving. In: ICCV, pp. 388–393 (2001)Google Scholar
  11. 11.
    Stevens, M.R., Culbertson, W.B., Malzbender, T.: A histogram-based color consistency test for voxel coloring. In: ICPR, pp. 118–121 (2002)Google Scholar
  12. 12.
    Yang, R., Pollefeys, M., Welch, G.: Dealing with textureless regions and specular highlight: A progressive space carving scheme using a novel photo-consistency measure. In: ICCV, pp. 576–584 (2003)Google Scholar
  13. 13.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing. Prentice-Hall, Englewood Cliffs (2002)Google Scholar
  14. 14.
    Szeliski, R.: Rapid octree construction from image sequences. Computer Vision, Graphics and Image Processing: Image Understanding 58, 23–32 (1993)CrossRefGoogle Scholar
  15. 15.
    Prock, A.C., Dyer, C.R.: Towards real-time voxel coloring. In: Image Understanding Workshop, pp. 315–321 (1998)Google Scholar
  16. 16.
    Sainz, M., Bagherzadeh, N., Susin, A.: Hardware accelerated voxel carving. In: SIACG, pp. 289–297 (2002)Google Scholar
  17. 17.
    Culbertson, W.B., Malzbender, T., Slabaugh, G.G.: Generalized voxel coloring. In: Workshop on Vision Algorithms, pp. 100–115 (1999)Google Scholar
  18. 18.
    Eisert, P., Steinbach, E., Girod, B.: Multi-hypothesis, volumetric reconstruction of 3-d objects from multiple calibrated camera views. In: ICASSP, pp. 3509–3512 (1999)Google Scholar
  19. 19.
    Yang, R., Pollefeys, M.: Multi-resolution real-time stereo on commodity graphics hardware. In: CVPR, pp. 211–217 (2003)Google Scholar
  20. 20.
    OpenGL extension registry,
  21. 21.
    Botsch, M., Hornung, A., Zwicker, M., Kobbelt, L.: High-quality surface splatting on today’s GPUs. In: Eurographics Symp. on Point-Based Graphics, pp. 17–24 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Alexander Hornung
    • 1
  • Leif Kobbelt
    • 1
  1. 1.Computer Graphics GroupRWTH Aachen UniversityGermany

Personalised recommendations