A Dynamic Programming Approach to Reconstructing Building Interiors

  • Alex Flint
  • Christopher Mei
  • David Murray
  • Ian Reid
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6315)


A number of recent papers have investigated reconstruction under Manhattan world assumption, in which surfaces in the world are assumed to be aligned with one of three dominant directions [1,2,3,4]. In this paper we present a dynamic programming solution to the reconstruction problem for “indoor” Manhattan worlds (a sub–class of Manhattan worlds). Our algorithm deterministically finds the global optimum and exhibits computational complexity linear in both model complexity and image size. This is an important improvement over previous methods that were either approximate [3] or exponential in model complexity [4]. We present results for a new dataset containing several hundred manually annotated images, which are released in conjunction with this paper.


Surface Orientation Wall Segment Dynamic Program Approach Orientation Estimate Dominant Direction 
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.


  1. 1.
    Coughlan, J., Yuille, A.: Manhattan world: compass direction from a single image by bayesian inference. In: CVPR, vol. 2, pp. 941–947 (1999)Google Scholar
  2. 2.
    Kǒsecká, J., Zhang, W.: Video compass. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part IV. LNCS, vol. 2353, pp. 476–490. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  3. 3.
    Furukawa, Y., Curless, B., Seitz, S., Szeliski, R.: Manhattan-world stereo. In: CVPR, pp. 1422–1429 (2009)Google Scholar
  4. 4.
    Lee, D.C., Hebert, M., Kanade, T.: Geometric reasoning for single image structure recovery. In: CVPR (2009)Google Scholar
  5. 5.
    Flint, A., Mei, C., Reid, I., Murray, D.: Growing semantically meaningful models for visual slam. In: CVPR (2010)Google Scholar
  6. 6.
    Hedau, V., Hoiem, D., Forsyth, D.: Recovering the spatial layout of cluttered rooms. In: ICCV, vol. 2 (2009)Google Scholar
  7. 7.
    Huffman, D.A.: Impossible objects as nonsense sentences. Machine Intelligence 6, 295–323 (1971)Google Scholar
  8. 8.
    Waltz, D.L.: Generating semantic descriptions from drawings of scenes with shadows. Technical report, MIT (1972)Google Scholar
  9. 9.
    Sugihara, K.: Mathematical structures of line drawings of polyhedrons. PAMI 4, 458–469 (1982)Google Scholar
  10. 10.
    Kanade, T.: A theory of origami world. Artificial Intelligence 13, 279–311 (1980)zbMATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    Hoiem, D., Efros, A.A., Hébert, M.: Geometric context from a single image. In: ICCV, pp. 654–661 (2005)Google Scholar
  12. 12.
    Saxena, A., Sun, M., Ng, A.Y.: Make3d: Learning 3d scene structure from a single still image. PAMI 31, 824–840 (2009)Google Scholar
  13. 13.
    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
  14. 14.
    Felzenszwalb, D., Veksler, O.: Tiered scene labeling with dynamic programming. In: CVPR (2010)Google Scholar
  15. 15.
    Criminisi, A.: Accurate visual metrology from single and multiple uncalibrated images. Springer, New York (2001)zbMATHGoogle Scholar
  16. 16.
    Kolmogorov, V., Zabih, R.: What energy functions can be minimized via graph cuts? PAMI (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Alex Flint
    • 1
  • Christopher Mei
    • 1
  • David Murray
    • 1
  • Ian Reid
    • 1
  1. 1.Dept. Engineering ScienceUniversity of OxfordOxfordUK

Personalised recommendations