Image-Based Modeling Using Viewpoint Entropy

  • Pere-Pau Vázquez
  • Miquel Feixast
  • Mateu Sbert
  • Wolfgang Heidrich

Abstract

We present a new method to automatically determine the correct camera placement positions in order to obtain a minimal set of views for Image-Based Rendering. The viewpoints should cover all visible polygons with an adequate quality, so that we sample the polygons at enough rate. This allows to avoid the excessive redundancy of the data existing in several other approaches. The localisation of interesting viewpoints is performed with the aid of an information theory-based measure, dubbed viewpoint entropy. This measure can be used to determine the amount of information seen from a viewpoint. We have also developed a greedy algorithm that aims to minimise the number of images needed to represent a scene.

In contrast to other approaches, our system uses a special preprocess for textures to avoid artifacts appearing in partially occluded textured polygons. Therefore no visible detail of these images is lost.

Keywords:

Image-Based Modeling Image-Based Rendering Viewpoint Selection Entropy. 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    L. McMillan and G. Bishop. Plenoptic modeling: An image-based rendering systemProc. of SIGGRAPH95 pages 39–46, August 1995.Google Scholar
  2. [2]
    L. McMillan. An Image-Based Approach to Three-Dimensional Computer Graphics, Ph.D. Dissertation. PhD, April 1997.Google Scholar
  3. [3]
    R.E. Blahut. Principles and Practice of Information Theory Addison-Wesley, 1987.Google Scholar
  4. [4]
    T.M. Cover and J.A. Thomas. Elements of Information Theory. Wiley 1991.CrossRefGoogle Scholar
  5. [5]
    Pere-Pau Vázquez, Miguel Feixas, Mateu Sbert, and Wolfgang Heidrich. Viewpoint selection using viewpoint entropy. In T.Ertl, B. Girod, G.Greiner, H. Niemann, and H.-P. Seidel, editors, Vision, Modeling, and Visualization2001. 2001.Google Scholar
  6. [6]
    S. Fleishman, D. Cohen-Or, and D. Lischinski. Automatic camera placement for image-based modeling. Computer Graphics Forum 19(2):101–110, Jun 2000MATHCrossRefGoogle Scholar
  7. [7]
    T. Kamada and S. Kawai. A simple method for computing general position in displaying three-dimensional objects. Computer Vision, Graphics, and Image Processing 41(1):43–56, January 1988.CrossRefGoogle Scholar
  8. [8]
    P. Barral, G. Dorme, and D. Plemenos. Scene understanding techniques using a virtual camera. In A. de Sousa and J.C. Torres, editors, Proc. Eurographics’00, short presentations, 2000.Google Scholar
  9. [9]
    G. Dorme. Study and implementation of 3D scenes comprehension techniques. PhD thesis, 2001Google Scholar
  10. [10]
    L. Wong, C. Dumont, and M. Abidi. Next best view system in a 3-d object modeling task. In Proc. International Symposium on Computational Intelligence in Robotics and Automation (CIRA) pages 306–311, 1999.Google Scholar
  11. [11]
    N.A. Massios and R.B. Fisher. A best next view selection algorithm incorporating a quality criterion. In Proc.of the Britsh Machine Vision Conference1998Google Scholar
  12. [12]
    B. AbidiRobots and Computer Vision: Algorithms, TechniquesAutomatic sensor placement. InProc. Intelligent Robots and Computer Vision: Algorithms, Techniques, Active Vision, and Materials Handling pages 387–398, 1995CrossRefGoogle Scholar
  13. [13]
    J.P. Grossman and William J. Dally. Point sample rendering. In George Drettakis and Nelson Max editors, editorsRendering Techniques’98 pages 181–192. Springer-Verlag, 1998.CrossRefGoogle Scholar
  14. [14]
    W. Stuerzlinger. Imaging all visible surfaces. In I. Scott MacKenzie and James Stewart, editorsProc. of the Conference on Graphics Interface (GI-99 pages 115–122, Toronto, Ontario, June 115–122 1999. CIPS.Google Scholar
  15. [15]
    D. Lischinski and A. Rappoport. Image-based rendering for non-diffuse synthetic scenes. In George Drettakis and Nelson Max editors, editors, Rendering Techniques’98 pages 301–314, 1998.CrossRefGoogle Scholar
  16. [16]
    V. Hlavac, A. Leonardis, and T. Werner. Automatic selection of reference views for image-based scene representations. InLecture Notes in Computer Science, pages 526–535, New York, NY, 1996. Springer Verlag. Proc. of European Conference on Computer Vision ‘86 (ECCV ‘86).Google Scholar
  17. [17]
    Jin-Xiang Chai, Xin Tong, Shing-Chow Chan, and Heung-Yeung Shum. Plenoptic sampling. InSIGGRAPH 2000, Computer Graphics Proceedings pages 307–318. ACM Press/ACM SIGGRAPH/Addison Wesley Longman, 2000.Google Scholar
  18. [18]
    J. O’Rourke. Art Gallery Theorems and Algorithms. Oxford University Press, New York, 1987.MATHGoogle Scholar
  19. [19]
    Robert M. Haralick and Linda G. Shapiro. Computer and Robot Vision, vol. 1. Addison-Welsey: Reading, MA, 1992Google Scholar
  20. [20]
    L. He J. Shade, S. Gortler and R. Szeliski. Layered depth images. In Computer Graphics Proceedings (Proc. SIGGRAPH ‘88), pages 231–242, July 1998.Google Scholar
  21. [21]
    Philippe Bekaert, Frank Suykens de Laet, Pieter Peers, and Vincent Masselus. Renderpark: A test-bed system for global illumination. available under http://www.cs.kuleuven.ac.be/cwis/research/graphics/RENDERPARK/
  22. [22]
    Szymon Rusinkiewicz and Marc Levoy. QSplat: A multiresolution point rendering system for large meshes. In Kurt Akeley, editorSiggraph 2000, Computer Graphics Proceedings Annual Conference Series, pages 343–352. ACM Press/ACM SIGGRAPH/Addison Wesley Longman, 2000.Google Scholar

Copyright information

© Springer-Verlag London 2002

Authors and Affiliations

  • Pere-Pau Vázquez
    • 1
  • Miquel Feixast
    • 1
  • Mateu Sbert
    • 1
  • Wolfgang Heidrich
    • 2
  1. 1.Universitat de GironaInstitut d’Informàtica i AplicacionsGirona
  2. 2.University of BritishColumbia

Personalised recommendations