Pop-up Modelling of Hazy Scenes

  • Lingyun ZhaoEmail author
  • Miles Hansard
  • Andrea Cavallaro
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9279)


This paper describes the construction of a layered scene-model, based on a single hazy image of an outdoor scene. A depth map and radiance image are estimated by standard dehazing methods. The radiance image is then segmented into a small number of clusters, and a corresponding scene-plane is estimated for each. This provides the basic structure of a 2.5-D scene model, without the need for multiple views, or image correspondences. We show that problems of gap-filling and depth blending can be addressed systematically, with respect to the layered depth-structure. The final models, which resemble cardboard ‘pop-ups’, are visually convincing. An HTML5/WebGL implementation is described, and subjective depth-preferences are tested in a psychophysical experiment.


Layered scene models Dehazing Visualization WebGL 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    He, K., Sun, J., Tang, X.: Single Image Haze Removal Using Dark Channel Prior. IEEE Trans. PAMI 33(12), 2341–2353 (2011)CrossRefGoogle Scholar
  2. 2.
    Debevec, P.E., Taylor, C.J., Malik, J.: Modeling and rendering architecture from photagraphs: a hybrid geometry and image-based approach. In: Proc. ACM SIGGRAPH, pp. 11–20 (1996)Google Scholar
  3. 3.
    Cipolla, R., Robertson, D., Boyer, E.: Photobuilder - 3D models of architectural scenes form uncalibrated images. In: Proc. IEEE Conference on Multimedia Computing and Systems, pp. 25–31 (1999)Google Scholar
  4. 4.
    Hoiem, D., Efros, A., Hebert, M.: Automatic photo pop-up. In: Proc. ACM SIGGRAPH, pp. 577–584 (2005)Google Scholar
  5. 5.
    Hoiem, D., Efros, A., Hebert, M.: Putting objects in perspective. In: Proc. CVPR, pp. 3–15 (2006)Google Scholar
  6. 6.
    Saxena, A., Chuang, S.H., Ng, A.Y.: Learning depth from single monocular images. In: Proc. NIPS, vol. 18, pp. 1161–1168 (2005)Google Scholar
  7. 7.
    Saxena, A., Chuang, S.H., Ng, A.Y.: 3D depth reconstruction from a single still image. In: Proc. IJCAI, pp. 53–69 (2007)Google Scholar
  8. 8.
    Saxena, A., Sun, M., Ng, A.Y.: Learning 3D scene structure from a single still image. In: Proc. ICCV, pp. 1–8 (2007)Google Scholar
  9. 9.
    Criminisi, A.: Objecte removal by exemplar-based inpainting. In: Proc. CVPR (2003)Google Scholar
  10. 10.
    Fischler, M., Bolles, R.: Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. Communications of the ACM 24, 381–395 (1981)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Schnabel, R., Wahl, R., Klein, R.: Efficient RANSAC for Point-cloud Shape Detection. Computer Graphics Forum 26(2), 214–226 (2007)CrossRefGoogle Scholar
  12. 12.
    Yingyang, M., Förstner, W.: Plane Detection in Point Cloud Data. Technical report, Institute of Geodesy and Geoinformation, University of Bonn (2010)Google Scholar
  13. 13.
    Criminisi, A., Reid, I., Zisserman, A.: Single View Metrology. Int. Journal of Computer Vision 40(2), 123–148 (2000)CrossRefzbMATHGoogle Scholar
  14. 14.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press (2004)Google Scholar
  15. 15.
    Horry, Y., Anjyo, K.I., Arai, K.: Tour into the picture: using a spidery mesh interface to make animation from a single image. In: Proc. ACM SIGGRAPH, pp. 225–232 (1997)Google Scholar
  16. 16.
    Liebowitz, D., Criminisi, A., Zisserman, A.: Creating architectural models from images. In: Proc. Eurographics, vol. 18, pp. 39–50 (1999)Google Scholar
  17. 17.
    Zhang, L., Dugas-Phocion, G., Samson, J., Seitz, S.: Single view modeling of free-form scenes. In: Proc. CVPR, pp. 990–997 (2001)Google Scholar
  18. 18.
    Rother, C., Kolmogorov, V., Blake, A.: Grab-Cut: Interactive foreground extraction using iterated graph cuts. ACM Trans. Computer Graphics 23(3), 309–314 (2004)CrossRefGoogle Scholar
  19. 19.
    Wang, J.Y.A., Adelson, E.H.: Representing Moving Images with Layers. IEEE Trans. Image Processing 3(5), 625–638 (1994)CrossRefGoogle Scholar
  20. 20.
    Swirski, L., Richardt, C., Dodgson, N.A.: Layered Photo Pop-Up. SIGGRAPH Posters (2011)Google Scholar
  21. 21.
    Szeliski, R., Golland, P.: Stereo matching with transparency and matting. In: Proc. ICCV, pp. 517–524 (1998)Google Scholar
  22. 22.
    Three JavaScript Library.

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Centre for Intelligent SensingQueen Mary University of LondonLondonUK

Personalised recommendations