Abstract
The problem addressed in this paper is related to displaying a real 3-D scene from any viewpoint. To display a scene, a relatively sparse set of 2-D reference views is stored. The images that are inbetween the reference views are obtained by interpolation of coordinates and brightness (colour). This approach is able to generate the scene representation and render images automatically and efficiently even for complex scenes of 3-D objects. This is possible since the processing time does not depend on the complexity of the scene as there is no attempt to understand the semantics of images.
In this paper we present a novel approach to automatically determine a minimal set of views from which the complete scene can be rendered. The method consists of two procedures: view-interval growing and selection. The first procedure independently searches for the intervals from which large portions of the scene can be rendered. These intervals are then passed to the selection procedure, which selects the minimal set of necessary views. The selection procedure is posed as an optimization problem that minimizes the number of reference views and the error due to the interpolation.
We are primarily indebted to Prof. Roger Hersch from the EPFL Lausanne in Switzerland who initiated the whole project and mediated T. Werner's support from the Swiss National Fund, grant 83H-036863. We were supported by the Grant Agency of the Czech Republic, grants 102/93/0954, 102/95/1378, and the EU grant Copernicus No. 1068. A. Leonardis' work was supported partly by the Austrian National Fonds zur Förderung der wissenschaftlichen Forschung under grant S7002MAT, the Ministry of Science and Technology of Republic of Slovenia (Project J2-6187), and by U.S.-Slovene Joint Board (Project #95-158). We are grateful to Tomáš Pajdla, Walter Kropatsch, and Radim Šára for discussions.
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
S.E. Chen and L. Williams. View interpolation for image synthesis. In Proceedings of the SIGRAPH'93, pages 279–288, 1993.
F. Glover and M. Laguna. Tabu search. In C. R. Reeves, editor, Modern heuristic techniques for combinatorial problems, pages 70–150. Blackwell Scientific Publications, 1993.
Shi-Kuo Chang. Principles of Pictoral Information Systems Design. Prentice-Hall, Englewood Cliffs, New Jersey, USA, 1989.
Ingemar J. Cox, Sunita Hingorani, Bruce M. Maggs, and Satish B. Rao. Stereo without disparity gradient smoothing: a Bayesian sensor fusion solution. In British Machine Vision Conference, pages 337–346, Berlin, 1992. Springer-Verlag.
T. Kanade, P.J. Narayanan, and P.W. Rander. Virtualized reality: Concepts and early results. In Proceedings of the Visual Scene Representation Workshop, Boston, MA., USA, June 24, page 8. available via http://www.cis.upenn.edu/eero/VisSceneRep95.html, 1995.
A. Leonardis. Image Analysis Using Parametric Models. PhD thesis, University of Ljubljana, Slovenia, March 1993.
Stéphane Laveau and Olivier 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. Also the technical report, available on ftp.inria.fr.
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, page 8. available via http: //www.cis.upenn.edu/eero/VisSceneRep95.html, 1995.
A. Shashua. Trilinearity in visual recognition by alignment. In Proceedings of the 3rd European Conference on Computer Vision, Stockholm, Sweden, volume 1, pages 479–484. SV, 1994.
M. Stricker and A. Leonardis. ExSel++: A general framework to extract parametric models. In V. Hlaváč and R. Šára, editors, 6th CAIP'95, number 970 in Lecture Notes in Computer Science, pages 90–97, Prague, Czech Republic, September 1995. Springer.
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 ICCV95, pages 957–962, Boston, USA, June 1995. IEEE Press.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hlaváč, V., Leonardis, A., Werner, T. (1996). Automatic selection of reference views for image-based scene representations. In: Buxton, B., Cipolla, R. (eds) Computer Vision — ECCV '96. ECCV 1996. Lecture Notes in Computer Science, vol 1064. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0015563
Download citation
DOI: https://doi.org/10.1007/BFb0015563
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61122-6
Online ISBN: 978-3-540-49949-7
eBook Packages: Springer Book Archive