Abstract
Image-based scene representation is believed to be an alternative to the 3-D model reconstruction and rendering. In attempt to compare generality of image-based and model-based approaches we argue that it is plausible to distinguish three approaches to 3-D scene visualization: image interpolation, image extrapolation, and 3-D model reconstruction and rendering. We advocate that image extrapolation is a useful trade-off between simple but limited interpolation and general but difficult 3-D model reconstruction and rendering. Image extrapolation is able to visualize correctly the part of a 3-D scene that is visible from two reference images. In fact, it is equivalent to reconstructing a projective 3-D model from two reference images and rendering it. In the second part of the work, we present an algorithm for rendering a projective model. Our approach is more efficient than the ray-tracing-like algorithm by Laveau and Faugeras [6]. We show that visibility can be solved by z-buffering, and that virtual images can be synthesized by transferring triangles from a reference image via a homography or an affinity. Such algorithms are often supported by hardware on graphics work stations, which makes a step towards the real-time synthesis. The results are presented for real scenes.
This research was supported by the Grant Agency of the Czech Republic, grants 102/97/0480 and 102/97/0855, by European Union, grant Copernicus CP941068, and by the Czech Ministry of Education, grant VS96049.
Chapter PDF
Keywords
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
Shenchang Eric Chen and Lance Williams. View interpolation for image synthesis. In James T. Kajiya, editor, Computer Graphics (SIGGRAPH '93 Proceedings), volume 27, pages 279–288, August 1993.
O. Faugeras and B. Mourrain. On the geometry and algebra of the point and line correspondences between N images. In Proceedings of the 5th International Conference on Computer Vision, pages 951–956, Boston, USA, June 1995. IEEE.
Olivier D. Faugeras, Q. T. Luong, and S. J. Maybank. Camera self-calibration: Theory and experiments. In European Conference on Computer Vision, pages 321–333, 1992.
R. I. Hartley. A linear method for reconstruction from lines and points. In Proceedings of the 5th International Conference on Computer Vision, pages 882–887, Boston USA, June 1995. IEEE Computer Society Press.
R. Kumar, P. Anadan, M. Irani, J. Bergen, and K. Hanna. Representation of scenes from collection of images. In Proceedings of the Visual Scene Representation Workshop, Boston, MA., USA, June 24, pages 10–17. IEEE Computer Society Press, 1995.
S. Laveau and O. Faugeras. 3-D scene representation as a collection of images. In Proc. of 12th International Conf. on Pattern Recognition, Jerusalem, Israel, pages 689–691, October 9–13 1994.
S. Laveau and O. Faugeras. Oriented projective geometry for computer vision. In Proceedings of the 4th European Conference on Computer Vision'96, volume I, pages 147–156. Springer-Verlag, April 1996.
Leonard McMillan and Gary Bishop. Plenoptic modeling: An image-based rendering system. In Robert Cook, editor, SIGGRAPH'95 Conference Proceedings, pages 39–46. Addison Wesley, August 1995.
Charlie Rothwell, Gabriela Csurka, and Olivier Faugeras. A comparison of projective reconstruction methods for pairs of views. Technical Report 2538, INRIA, Sophia-Antipolis, France, April 1995.
S. M. Seitz and C. R. Dyer. Physically-valid view synthesis by image interpolation. In Proceedings of the Visual Scene Representation Workshop, Boston, MA., USA, June 24, pages 18–27. IEEE Computer Society Press, 1995.
A. Shashua. On geometric and algebraic aspects of 3D affine and projective structures from perspective 2D views. Technical Report AI Memo No. 1405, Massachusetts Institute of Technology, Artifical Intelligence Laboratory, July 1993.
A. Shashua and M. Werman. Trilinearity of three perspective views and its associated tensor. In Proceedings of the 5th International Conference on Computer Vision, pages 920–925. IEEE Computer Society Press, May 1995.
M. Spetsakis and J. Alomoinos. A unified theory of structure from motion. In Proceedigs ARPA Image Understanding Workshop, pages 271–283, Pittsburg, PA, USA, 1990.
S. Ullman and R. Basri. Recognition by linear combination of models. IEEE Transactions of Pattern Analysis and Machine Intelligence, 13(10):992–1005, October 1991.
T. Werner, R.D. Hersch, and V. Hlaváč. Rendering real-world objects using view interpolation. In Proceedings of the 5th International Conference on Computer Vision, pages 957–962, Boston, USA, June 1995. IEEE Computer Society Press.
T. Werner, V. Hlaváč, A. Leonardis, and T. Pajdla. Selection of reference views for image-based representation. In Proceedings of the 13th International Conference on Pattern Recognition, volume I — Track A: Computer Vision, pages 73–77, Vienna, Austria, August 1996. IEEE Computer Society Press, Los Alamitos, CA., USA.
Tomáš Werner, Tomáš Pajdla, and Václav Hlaváč. Correspondence by tracking edges in a dense sequence for image-based scene representation. In Proceedings of the Czech Pattern Recognition Workshop '97, pages 64–68, Milovy, Czech Republic, Feb 1997. Czech Pattern Recognition Society. Available from http://cmp.felk.cvut.cz.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Werner, T., Pajdla, T., Hlaváč, V. (1998). Efficient 3-D scene visualization by image extrapolation. In: Burkhardt, H., Neumann, B. (eds) Computer Vision — ECCV’98. ECCV 1998. Lecture Notes in Computer Science, vol 1407. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0054754
Download citation
DOI: https://doi.org/10.1007/BFb0054754
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64613-6
Online ISBN: 978-3-540-69235-5
eBook Packages: Springer Book Archive