Title :
Photorealistic scene reconstruction by voxel coloring
Author :
Seitz, Steven M. ; Dyer, Charles R.
Author_Institution :
Dept. of Comput. Sci., Wisconsin Univ., Madison, WI, USA
Abstract :
A novel scene reconstruction technique is presented, different from previous approaches in its ability to cope with large changes in visibility and its modeling of intrinsic scene color and texture information. The method avoids image correspondence problems by working in a discretized scene space whose voxels are traversed in a fixed visibility ordering. This strategy takes full account of occlusions and allows the input cameras to be far apart and widely distributed about the environment. The algorithm identifies a special set of invariant voxels which together form a spatial and photometric reconstruction of the scene, fully consistent with the input images. The approach is evaluated with images from both inward- and outward-facing cameras
Keywords :
computer vision; image reconstruction; discretized scene space; fixed visibility ordering; intrinsic scene color; invariant voxels; occlusions; photorealistic scene reconstruction; scene reconstruction technique; texture information; voxel coloring; voxels; Application software; Cameras; Computer vision; Image reconstruction; Image resolution; Layout; Pixel; Shape; Stereo image processing; World Wide Web;
Conference_Titel :
Computer Vision and Pattern Recognition, 1997. Proceedings., 1997 IEEE Computer Society Conference on
Conference_Location :
San Juan
Print_ISBN :
0-8186-7822-4
DOI :
10.1109/CVPR.1997.609462