Volumetric Warping for Voxel Coloring on an Infinite Domain
Starting with a set of calibrated photographs taken of a scene, voxel coloring algorithms reconstruct three-dimensional surface models on a finite spatial domain. In this paper, we present a method that warps the voxel space, so that the domain of the reconstruction extends to an infinite or semi-infinite volume. Doing so enables the reconstruction of objects far away from the cameras, as well as reconstruction of a background environment. New views synthesized using the warped voxel space have improved photo-realism.
KeywordsWarping Function Reconstruction Volume Interior Space Epipolar Geometry Outdoor Scene
Unable to display preview. Download preview PDF.
- 1.J. Blinn and M. Newell, “Texture and Reflection on Computer Generated Images,” Communications of ACM, Vol. 19, No. 10, pp. 542–547, Oct. 1976.Google Scholar
- 2.W. B. Culbertson, T. Malzbender, and G. Slabaugh, “Generalized Voxel Coloring,” Vision Algorithms: Theory and Practice, Springer-Verlag Lecture Notes in Computer Science, pp. 100–115, 1999.Google Scholar
- 3.N. Greene, “Environment Mapping and Other Applications of World Projections, ” IEEE Computer Graphics and Applications, pp. 21–29, Nov. 1986.Google Scholar
- 4.M. Kimura, H. Satio, and T. Kanade, “3D Voxel Construction Based on Epipolar Geometry” Proc. ICIP, pp. 135–139, 1999.Google Scholar
- 5.K. Kutulakos and S. Seitz, “A Theory of Shape by Space Carving,” Proc. ICCV,pp. 307–314, 1999.Google Scholar
- 6.H. Saito and T. Kanade, “Shape Reconstruction in Projective Grid Space from Large Number of Images,” Proc. CVPR, pp. 49–54, 1999.Google Scholar
- 7.S. Seitz and C. Dyer, “Photorealistic Scene Reconstruction by Voxel Coloring,” International Journal of Computer Vision, Vol. 35, No. 2, pp. 151–173, Feb. 1999.Google Scholar