Implicit Representation and Scene Reconstruction from Probability Density Functions

Seitz, Steven M.; Anandan, P.

doi:10.1109/CVPR.1999.784604

Implicit Representation and Scene Reconstruction from Probability Density Functions

Steven M. Seitz, P. Anandan

CVPR 1999 pp. 2028-2034

doi:10.1109/CVPR.1999.784604 /cvpr/1999/seitz1999cvpr-implicit/

Abstract

A technique is presented for representing linear features as probability density functions in two or three dimensions. Three chief advantages of this approach are (1) a unified representation and algebra for manipulating points, lines, and planes, (2) seamless incorporation of uncertainty information, and (3) a very simple recursive solution for maximum likelihood shape estimation. Applications to uncalibrated affine scene reconstruction are presented, with results on images of an outdoor environment.

PDF CVPR Semantic Scholar

Cite

Text

Seitz and Anandan. "Implicit Representation and Scene Reconstruction from Probability Density Functions." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999. doi:10.1109/CVPR.1999.784604

Markdown

[Seitz and Anandan. "Implicit Representation and Scene Reconstruction from Probability Density Functions." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999.](https://mlanthology.org/cvpr/1999/seitz1999cvpr-implicit/) doi:10.1109/CVPR.1999.784604

BibTeX

@inproceedings{seitz1999cvpr-implicit,
  title     = {{Implicit Representation and Scene Reconstruction from Probability Density Functions}},
  author    = {Seitz, Steven M. and Anandan, P.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1999},
  pages     = {2028-2034},
  doi       = {10.1109/CVPR.1999.784604},
  url       = {https://mlanthology.org/cvpr/1999/seitz1999cvpr-implicit/}
}