ML Anthology

A Probabilistic Framework for Space Carving

Adrian Broadhurst, Tom Drummond, Roberto Cipolla
ICCV 2001 pp. 388-393
doi:10.1109/ICCV.2001.10017 /iccv/2001/broadhurst2001iccv-probabilistic/

Abstract

This paper introduces a new probabilistic framework for Space Carving. In this framework each voxel is assigned a probability, which is computed by comparing the likelihoods for the voxel existing and not existing. This new framework avoids many of the difficulties associated with the original Space Carving algorithm. Specifically, it does not need a global threshold parameter, and it guarantees that no holes will be carved in the model. This paper also proposes that a voxel-based thick texture is a realistic and efficient representation for scenes which contain dominant planes. The algorithm is tested using both real and synthetic data, and both qualitative and quantitative results are presented.

ICCV Semantic Scholar

Cite

Text

Broadhurst et al. "A Probabilistic Framework for Space Carving." IEEE/CVF International Conference on Computer Vision, 2001. doi:10.1109/ICCV.2001.10017

Markdown

[Broadhurst et al. "A Probabilistic Framework for Space Carving." IEEE/CVF International Conference on Computer Vision, 2001.](https://mlanthology.org/iccv/2001/broadhurst2001iccv-probabilistic/) doi:10.1109/ICCV.2001.10017

BibTeX

@inproceedings{broadhurst2001iccv-probabilistic,
  title     = {{A Probabilistic Framework for Space Carving}},
  author    = {Broadhurst, Adrian and Drummond, Tom and Cipolla, Roberto},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2001},
  pages     = {388-393},
  doi       = {10.1109/ICCV.2001.10017},
  url       = {https://mlanthology.org/iccv/2001/broadhurst2001iccv-probabilistic/}
}