Advertisement

Image-Based Rendering by Virtual 1D Cameras

  • Naoyuki Ichimura
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5414)

Abstract

Image-based rendering (IBR) has been used to synthesize images corresponding to a new view point from stored images. Rendering methods based on a three-dimensional plenoptic function are attractive due to the simplicity of image capture. Only a few specific discussions, however, have been done for the scaling problem to correct aspect ratio distortion, which heavily affects the quality of a synthesized image. This paper presents a rendering algorithm with a scaling scheme, which is general in that it can handle arbitrary camera paths. We model a virtual camera by a set of one-dimensional (1D) cameras. The ray representation of the 1D camera enables us to devise a rendering algorithm for the cases where the camera paths to create ray databases are arbitrary curves. We conclude with experimental results that demonstrate the usefulness of the proposed algorithm.

Keywords

View Plane Camera Motion Distortion Correction World Coordinate System Virtual Camera 
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.

References

  1. 1.
    Shum, H.Y., Chan, S.C., Kang, S.B.: Image-Based Rendering. Springer, Heidelberg (2007)zbMATHGoogle Scholar
  2. 2.
    Adelson, E.H., Bergen, J.R.: The Plenoptic Function and the Elements of Early Vision, pp. 3–20. MIT Press, Cambridge (1991)Google Scholar
  3. 3.
    Levoy, M., Hanrahan, P.: Light field rendering. In: Proc. SIGGRAPH 1996, pp. 31–42 (1996)Google Scholar
  4. 4.
    Gortler, S.J., Grzeszczuk, R., Szeliski, R., Cohen, M.F.: The lumigraph. In: Proc. SIGGRAPH 1996, pp. 43–54 (1996)Google Scholar
  5. 5.
    Shum, H.Y., He, L.W.: Rendering with concentric mosaics. In: Proc. SIGGRAPH 1999, pp. 299–306 (1999)Google Scholar
  6. 6.
    Weinshall, D., Lee, M.S., Brodsky, T., Trajkovic, M.: New view generation with a bi-centric camera. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 614–628. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  7. 7.
    Bakstein, H., Pajdla, T., Vecerka, D.: Rendering almost perspective views from a sparse set of omnidirectional images. In: Proc. BMVC, pp. 241–250 (2003)Google Scholar
  8. 8.
    Zomet, A., Feldman, D., Peleg, S., Weinshall, D.: Mosaicing new views: The cross-slits projection. IEEE Trans. PAMI 25(6), 741–753 (2003)CrossRefGoogle Scholar
  9. 9.
    Bakstein, H., Pajdla, T.: Rendering novel views from a set of omnidirectoinal mosaic images. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition Workshop (CVPRW 2003), pp. 74–79 (2003)Google Scholar
  10. 10.
    Bakstein, H., Pajdla, T.: Omnidirectional image-based rendering. In: Proc. Computer Vision Winter Workshop (CVWW 2006), pp. 99–104 (2006)Google Scholar
  11. 11.
    Buehler, C., Bosse, M., McMillan, L., Gortler, S., Cohen, M.: Unstructured lumigraph rendering. In: Proc. SIGGRAPH 2001, pp. 425–432 (2001)Google Scholar
  12. 12.
    Isaksen, A., McMillan, L., Gortler, S.J.: Dynamically reparameterized light fields. In: Proc. SIGGRAPH 2000, pp. 297–306 (2000)Google Scholar
  13. 13.
  14. 14.

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Naoyuki Ichimura
    • 1
  1. 1.National Institute of Advanced Industrial Science and Technology (AIST)TsukubaJapan

Personalised recommendations