A System for Image Based Rendering of Walk-throughs

  • Gaurav Agarwal
  • Dinesh Rathi
  • Prem K. Kalra
  • Subhashis Banerjee


We present a method for rendering novel views from a set of reference views under the assumption that scene surfaces can be approximated by planar patches. We use a set of sparse correspondences between the reference views to determine homographies through different planar patches using a clustering technique. We also obtain a segmentation of the scene in terms of planar regions visible from at least two views. Such segmentations explicitly resolve the visibility issues in novel view generation. We present results on rendering of realistic walk-through sequences for both indoor and outdoor scenes which demonstrate the applicability of our method.


Reference Image Target Image Epipolar Line Epipolar Geometry Outdoor Scene 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Image-Based Modeling, Rendering, and Lighting, SIGGRAPH Course 39,SIGGRAPH, 1999.Google Scholar
  2. [2]
    E. H. Adelson and J. R. Bergen, “The Plenoptic function and the Elements of Early Vision,” Computational Models of Visual Processing, Chapter 1, Edited by Michael Landy and J. Anthony Movshon. The MIT Press, Cambridge, Mass. 1991.Google Scholar
  3. [3]
    S. E. Chen and L. Williams, “View Interpolation for Image Synthesis,” SIGGRAPH, 1994.Google Scholar
  4. [4]
    P. E. Debevec, C. J. Taylor and J. Malik, “Modeling and Rendering Architecture from Photographs SIGGRAPH, 1996.Google Scholar
  5. [5]
    O. Faugeras, Three-Dimensional Computer Vision: A Geometric Viewpoint, The MIT Press, 1996.Google Scholar
  6. [6]
    C. Harris and M. Stevens, “A Combined Corner and Edge Detector,” Proc. 4th Alvey Vision Conference,pp. 153–158, 1988.Google Scholar
  7. [7]
    R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, 2000.Google Scholar
  8. [8]
    S. Laveau and O. D. Faugeras, “3-D Scene Representation as a Collection of Images and Fundamental Matrices,” INRIA, Technical Report No. 2205, 1994.Google Scholar
  9. [9]
    M. Lhuillier and L. Quan, “Image Interpolation by Joint View Triangulation,” CVPR, 1999.Google Scholar
  10. [10]
    L. McMillan, An Image-Based Approach to Three Dimensional Computer Graphics,Ph.D thesis, University of North Carolina at Chapel Hill, 1997 (Technical Report TR97–013).Google Scholar
  11. [11]
    L. McMillan, “Computing Visibility Without Depth,” UNC Technical Report, TR95–047, University of North Carolina, 1995.Google Scholar
  12. [12]
    L. McMillan and G. Bishop, “Plenoptic Modeling: An Image Based rendering System,”SIGGRAPH, 1995.Google Scholar
  13. [13]
    L. McMillan and G. Bishop, “Shape as a Perturbation to Projective Mapping,” UNC Technical Report, TR95–046, University of North Carolina, 1995.Google Scholar
  14. [14]
    S. M. Seitz and C. R. Dyer, “View Morphing,” SIGGRAPH, 1996.Google Scholar
  15. [15]
    R. Szeliski, “Image Mosaicing for Tele-Reality Applications,” DEC and Cambridge Research Lab. Technical Report„ CRL 94/2, 1994.Google Scholar

Copyright information

© Springer-Verlag London 2002

Authors and Affiliations

  • Gaurav Agarwal
    • 1
  • Dinesh Rathi
    • 1
  • Prem K. Kalra
    • 1
  • Subhashis Banerjee
    • 1
  1. 1.Department of Computer Science and EngineeringIndian Institute of TechnologyNew DelhiIndia

Personalised recommendations