Automatic multiperspective images

ABSTRACT

Multiperspective images generated from a collection of photographs or a videostream can be used to effectively summarize long, roughly planar scenes such as city streets. The final image will span a larger field of view than any single input image. However, common projections used to make these images, including cross-slits and pushbroom projections, may suffer from depth-related distortions in non-planar scenes. In this paper, we use an aspect-ratio distortion metric to compare these images to standard perspective projections. By minimizing this error metric we can automatically define the picture surface and viewpoints of a multiperspective image that reduces distortion artifacts. This optimization requires only a coarse estimate of scene geometry which can be provided as a depth map or a 2D spatial importance map defining interesting parts of the scene. These maps can be automatically constructed in most cases, allowing rapid generation of images of very long scenes.

References

1. A9: Blockview, 2005. http://maps.a9.com.
2. CROW F. C.: Summed-area tables for texture mapping. In SIGGRAPH '84: Proceedings of the 11th annual conference on Computer graphics and interactive techniques (New York, NY, USA, 1984), ACM Press, pp. 207-212.
3. FELDMAN D., ZOMET A.: Least Distorted Mosaics. Tech. Rep. 2003-71, Hebrew University, 2003.
4. FELDMAN D., ZOMET A., WEINSHALL D., PELEG S.: New view synthesis with non-stationary mosaicing. In MIRAGE (2003).
5. MEZA J. C.: Opt++: An Object-Oriented Class Library for Nonlinear Optimization. Tech. Rep. SAND83-8212, Sandia National Laboratories, Livermore, CA, March 1994.
6. MICROSOFT: Live! Local Preview, 2006. http://preview.live.local.com.
7. PIPONI D.: Automatic differentiation, c++ templates, and photogrammetry. In The Journal of Graphics Tools (2004), vol. 9.
8. RAV-ACHA A., SHOR Y., PELEG S.: Mosaicing with parallax using time warping. In Image and Video Registration (Washington, DC, July 2004).
9. RADEMACHER P., BISHOP G.: Multiple-center-of projection images. Computer Graphics 32, Annual Conference Series (1998), 199-206.
10. ROMAN A., GARG G., LEVOY M.: Interactive design of multi-perspective images for visualizing urban landscapes. In Proceedings of the IEEE Vis 2004 (2004).
11. SWAMINATHAN R., GROSSBERG M. D., NAYAR S. K.: A perspective on distortions. In CVPR (2) (2003), pp. 594- 601.
12. SEITZ S. M., KIM J.: Multiperspective imaging. IEEE Comput. Graph. Appl. 23, 6 (2003), 16-19.
13. UNIVERSITY OF HANNOVER: Voodoo camera tracker, 2005. http://www.digilab.uni-hannover.de/docs/manual.html.
14. WOOD D. N., FINKELSTEIN A., HUGHES J. F., THAYER C. E., SALESIN D. H.: Multiperspective panoramas for cel animation. In Proc. SIGGRAPH (1997), pp. 243-250.
15. WEXLER Y., SIMAKOV D.: Space-time scene manifolds. In Tenth IEEE International Conference on Computer Vision (ICCV'05) (2005), vol. 1, pp. 858-863.
16. YU J., MCMILLAN L.: A framework for multiperspective rendering. In Eurographics Symposium on Rendering (Norrkoping, Sweden, 2004).
17. ZOMET A., FELDMAN D., PELEG S., WEINSHALL D.: Mosaicing new views: The crossed-slits projection. IEEE Transactions on Pattern Analysis and Machine Intelligence 25, 6 (2003), 741-754.
18. ZHENG J. Y.: Digital route panoramas. IEEE MultiMedia 10, 03 (2003), 57-67.

Index Terms

• Computing methodologies

  • Artificial intelligence

    • Computer vision

      • Image and video acquisition

        • 3D imaging

  • Computer graphics

    • Animation

    • Image manipulation

    • Rendering