ML Anthology

Multi-Scale Structure from Multi-Views by Δ2G Filtered 3D Voting

Takeaki Y. Mori, Satoshi Suzuki, Tsutomu Horikoshi, Takayuki Yasuno
CVPR 1993 pp. 662-663
doi:10.1109/CVPR.1993.341039 /cvpr/1993/mori1993cvpr-multi/

Abstract

A multiscale 3-D structure recovery method is proposed. It divides the scene space into voxels and votes for them using the sight lines of the camera from coarse to fine. The mechanism behind the influence of the image quantization error and the position error of the camera's optical center is analyzed. Both errors can be diminished by /spl Delta//sup 2/G filtering the voted voxel space. A multiscale 3-D structure of objects is successfully generated from a real image sequence of six frames using this method.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

CVPR Semantic Scholar

Cite

Text

Mori et al. "Multi-Scale Structure from Multi-Views by Δ2G Filtered 3D Voting." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993. doi:10.1109/CVPR.1993.341039

Markdown

[Mori et al. "Multi-Scale Structure from Multi-Views by Δ2G Filtered 3D Voting." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993.](https://mlanthology.org/cvpr/1993/mori1993cvpr-multi/) doi:10.1109/CVPR.1993.341039

BibTeX

@inproceedings{mori1993cvpr-multi,
  title     = {{Multi-Scale Structure from Multi-Views by Δ2G Filtered 3D Voting}},
  author    = {Mori, Takeaki Y. and Suzuki, Satoshi and Horikoshi, Tsutomu and Yasuno, Takayuki},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1993},
  pages     = {662-663},
  doi       = {10.1109/CVPR.1993.341039},
  url       = {https://mlanthology.org/cvpr/1993/mori1993cvpr-multi/}
}