21/2 D Scene Reconstruction of Indoor Scenes from Single RGB-D Images

  • Natalia Neverova
  • Damien Muselet
  • Alain Trémeau
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7786)


Using the Manhattan world assumption we propose a new method for global 21/2D geometry estimation of indoor environments from single low quality RGB-D images. This method exploits both color and depth information at the same time and allows to obtain a full representation of an indoor scene from only a single shot of the Kinect sensor. The main novelty of our proposal is that it allows estimating geometry of a whole environment from a single Kinect RGB-D image and does not rely on complex optimization methods. This method performs robustly even in the conditions of low resolution, significant depth distortion, nonlinearity of depth accuracy and presence of noise.


3D reconstruction RGB-D Images Manhattan World 


  1. 1.
    Coughlan, J.M., Yuille, A.L.: Manhattan world: Compass direction from a single image by bayesian inference. In: IEEE International Conference on Computer Vision (ICCV), pp. 1–10. IEEE Press, New York (1999)Google Scholar
  2. 2.
    Oliva, A., Torralba, A.: Depth estimation from image structure. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 1226–1238 (2002)CrossRefGoogle Scholar
  3. 3.
    Saxena, A., Chung, S., Ng, A.Y.: Learning depth from single monocular images. In: Neural Information Processing Systems (NIPS), vol. 18. MIT Press (2005)Google Scholar
  4. 4.
    Delage, E., Lee, H., Ng, A.Y.: A dynamic bayesian network model for autonomous 3D reconstruction from a single indoor image. In: CVPR Conference (2006)Google Scholar
  5. 5.
    Barinova, O., Konushin, V., Yakubenko, A., Lee, K., Lim, H., Konushin, A.: Fast Automatic Single-View 3-d Reconstruction of Urban Scenes. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 100–113. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  6. 6.
    Hoiem, D., Efros, A.A., Hebert, M.: Automatic photo pop-up. In: SIGGRAPH Conference (2005)Google Scholar
  7. 7.
    Torralba, A., Sinha, P.: Statistical context priming for object detection. In: ICCV Conference (2001)Google Scholar
  8. 8.
    Kien, D.: A review of 3d reconstruction from video sequences. University of Amsterdam ISIS Technical Report Series (2005)Google Scholar
  9. 9.
    Pollefeys, M.: Visual 3d modelling from images. Tutorial notes. Technical report (2007)Google Scholar
  10. 10.
    Gallup, D., Frahm, J., Mordohai, P., Yang, Q., Pollefeys, M.: Real-time plane-sweeping stereo with multiple sweeping directions. In: CVPR Conference (2007)Google Scholar
  11. 11.
    Sinha, S.N., Steedly, D., Szelinski, R.: Piecewise planar stereo for image-based rendering. In: ICCV Conference, pp. 1881–1888 (2009)Google Scholar
  12. 12.
    Olufs, S., Vincze, M.: Robust Room-Structure estimation in Manhattan-like Environments from dense 2.5 range data. In: WACV Workshop, pp. 118–124 (2011)Google Scholar
  13. 13.
    Paris, S., Durand, F.: A Fast Approximation of the Bilateral Filter Using a Signal Processing Approach. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 568–580. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  14. 14.
    Silberman, N., Fergus, R.: Indoor scene segmentation using a structured light sensor. In: ICCV Workshop, pp. 601–608 (2011)Google Scholar
  15. 15.
    Van de Weijer, J., Gevers, T., Smeulders, A.W.M.: Robust photometric invariant features from the color tensor. IEEE Transactions on Image Processing 15(1), 118–127 (2006)CrossRefGoogle Scholar
  16. 16.
    Kovesi, P.D.: MATLAB and Octave Functions for Computer Vision and Image ProcessingGoogle Scholar
  17. 17.
    Rother, C.: A new approach to vanishing point detection in architectural environments. Image and Vision Computing 20(9-10), 647–655 (2002)CrossRefGoogle Scholar
  18. 18.
    Hedau, V., Hoiem, D., Forsyth, D.: Recovering the spatial layout of cluttered rooms. In: ICCV Conference, pp. 1849–1856 (2009)Google Scholar
  19. 19.
    Neverova, N., Konik, H.: Edge-based method for sharp region extraction from low depth of field images. In: VCIP Conference (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Natalia Neverova
    • 1
  • Damien Muselet
    • 1
  • Alain Trémeau
    • 1
  1. 1.Laboratoire Hubert Curien – UMR CNRS 5516University Jean MonnetSaint-ÉtienneFrance

Personalised recommendations