Advertisement

Fast Automatic Single-View 3-d Reconstruction of Urban Scenes

  • Olga Barinova
  • Vadim Konushin
  • Anton Yakubenko
  • KeeChang Lee
  • Hwasup Lim
  • Anton Konushin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5303)

Abstract

We consider the problem of estimating 3-d structure from a single still image of an outdoor urban scene. Our goal is to efficiently create 3-d models which are visually pleasant. We chose an appropriate 3-d model structure and formulate the task of 3-d reconstruction as model fitting problem. Our 3-d models are composed of a number of vertical walls and a ground plane, where ground-vertical boundary is a continuous polyline. We achieve computational efficiency by special preprocessing together with stepwise search of 3-d model parameters dividing the problem into two smaller sub-problems on chain graphs. The use of Conditional Random Field models for both problems allows to various cues. We infer orientation of vertical walls of 3-d model vanishing points.

Keywords

Ground Plane Vertical Wall Graph Node Virtual View Building Wall 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

978-3-540-88688-4_8_MOESM1_ESM.wmv (6.8 mb)
Supplementary material (6,994 KB)

References

  1. 1.
    Hoiem, D., Efros, A., Hebert, M.: Automatic photo pop-up. In: Proc. of ACM SIGGRAPH (2005)Google Scholar
  2. 2.
    Hoiem, D., Efros, A., Hebert, M.: Geometric context from a single image. In: Proc. of ICCV (2005)Google Scholar
  3. 3.
    Delage, E., Lee, H., Ng, A.: Automatic single-image 3d reconstructions of indoor manhattan world scenes. In: Proc. of ISRR (2005)Google Scholar
  4. 4.
    Delage, E., Lee, H., Ng, A.: A dynamic bayesian network model for autonomous 3d reconstruction from a single indoor image. In: Proc. of CVPR (2006)Google Scholar
  5. 5.
    Criminisi, A., Reid, I., Zisserman, A.: Single view metrology. IJCV 40 (2000)Google Scholar
  6. 6.
    Hoiem, D., Sten, A.N., Efros, A.A., Hebert, M.: Recovering Occlusion Boundaries from a Single Image. In: Proc. of ICCV (2007)Google Scholar
  7. 7.
    Saxena, A., Sun, M., Ng, A.: Learning 3-D Scene Structure from a Single Still Image. In: Proc. of ICCV workshop on 3D representation for Recognition (2007)Google Scholar
  8. 8.
    Saxena, A., Chung, S., Ng, A.: Depth Reconstruction from a Single Still Image. In: IJCV (2007)Google Scholar
  9. 9.
    Saxena, A., Chung, S., Ng, A.: Learning Depth from Single Monocular Images. In: Proc. of NIPS, vol. 18 (2005)Google Scholar
  10. 10.
    Canny, J.: A Computational Approach To Edge Detection. PAMI 8 (1986)Google Scholar
  11. 11.
    Kosecka, J., Zhang, W.: Video Compass. In: Proc. of ECCV, vol. 7, pp. 476–491 (2002)Google Scholar
  12. 12.
    Vezhnevets, V., Konushin, A., Ignatenko, A.: Interactive image-based urban modeling. In: Proc. of PIA, pp. 63–68 (2007)Google Scholar
  13. 13.
    Barinova, O., Kuzmishkina, A., Vezhnevets, A., Vezhnevets, V.: Learning class specific edges for vanishing point estimation. In: Proc. of Graphicon, pp. 162–165 (2007)Google Scholar
  14. 14.
    Chum, O., Matas, J., Kittler, J.: Locally Optimized RANSAC. In: DAGM Symposium on Pattern Recognition, vol. 25, pp. 236–243 (2003)Google Scholar
  15. 15.
    Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence 24, 5 (2002)Google Scholar
  16. 16.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proc. of ICML (2001)Google Scholar
  17. 17.
    Sutton, C., McCallum, A.: Piecewise training of undirected models. In: Proc. of UAI, vol. 21 (2005)Google Scholar
  18. 18.
    Shotton, J., Winn, J., Rother, C., Criminisi, A.: TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context. In: IJCV (2007)Google Scholar
  19. 19.
    Niculescu-Mizil, A., Caruana, R.: Obtaining Calibrated Probabilities from Boosting. In: Proc. of UAI, pp. 413–420 (2005)Google Scholar
  20. 20.
    Wasserman, L.: All of Nonparametric Statistics. Springer, Heidelberg (2006)zbMATHGoogle Scholar
  21. 21.
    Hulse, J., Khoshgoftaar, T., Napolitano, A.: Experimental perspectives on learning from imbalanced data. In: Proc. of ICML, pp. 935–942 (2007)Google Scholar
  22. 22.
    Viola, P., Jones, M.: Robust Real-time Object Detection. In: IJCV (2001)Google Scholar
  23. 23.
    Kang, H., Pyo, S., Anjyo, K., Shin, S.: Tour into the picture using a vanishing line and its extension to panoramic images. In: Proc. Eurographics, pp. 132–141 (2001)Google Scholar
  24. 24.
  25. 25.

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Olga Barinova
    • 1
  • Vadim Konushin
    • 2
  • Anton Yakubenko
    • 1
  • KeeChang Lee
    • 3
  • Hwasup Lim
    • 3
  • Anton Konushin
    • 1
  1. 1.Department of Computational Mathematics and Cybernetics, Graphics & Media LabMoscow State UniversityRussia
  2. 2.The Keldysh Institute of Applied Mathematic Russian Academy of SciencesRussia
  3. 3.Samsung Advanced Institute of TechnologySouth Korea

Personalised recommendations