Shape from the Light Field Boundary
Abstract
Ray-based representations of shape have received little attention in computer vision. In this paper we show that the problem of recovering shape from silhouettes becomes considerably simplified if it is formulated as a reconstruction problem in the space of oriented rays that intersect the object. The method can be used with both calibrated and uncalibrated cameras, does not rely on point correspondences to compute shape, and does not impose restrictions on object topology or smoothness.
Cite
Text
Kutulakos. "Shape from the Light Field Boundary." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997. doi:10.1109/CVPR.1997.609297Markdown
[Kutulakos. "Shape from the Light Field Boundary." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997.](https://mlanthology.org/cvpr/1997/kutulakos1997cvpr-shape/) doi:10.1109/CVPR.1997.609297BibTeX
@inproceedings{kutulakos1997cvpr-shape,
title = {{Shape from the Light Field Boundary}},
author = {Kutulakos, Kiriakos N.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {1997},
pages = {53-59},
doi = {10.1109/CVPR.1997.609297},
url = {https://mlanthology.org/cvpr/1997/kutulakos1997cvpr-shape/}
}