ML Anthology

Gauge Fixing for Accurate 3D Estimation

Daniel D. Morris, Ken-ichi Kanatani, Takeo Kanade
CVPR 2001 pp. II:343-350
doi:10.1109/CVPR.2001.990981 /cvpr/2001/morris2001cvpr-gauge/

Abstract

Computer vision techniques can estimate 3D shape from images, but usually only up to a scale factor. The scale factor must be obtained by a physical measurement of the scene or the camera motion. Using gauge theory, we show that how this scale factor is determined can significantly affect the accuracy of the estimated shape. And yet these considerations have been ignored in previous works where 3D shape accuracy is optimized. We investigate how scale fixing influences the accuracy of 3D reconstruction and determine what measurement should be made to maximize the shape accuracy.

CVPR Semantic Scholar

Cite

Text

Morris et al. "Gauge Fixing for Accurate 3D Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001. doi:10.1109/CVPR.2001.990981

Markdown

[Morris et al. "Gauge Fixing for Accurate 3D Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001.](https://mlanthology.org/cvpr/2001/morris2001cvpr-gauge/) doi:10.1109/CVPR.2001.990981

BibTeX

@inproceedings{morris2001cvpr-gauge,
  title     = {{Gauge Fixing for Accurate 3D Estimation}},
  author    = {Morris, Daniel D. and Kanatani, Ken-ichi and Kanade, Takeo},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2001},
  pages     = {II:343-350},
  doi       = {10.1109/CVPR.2001.990981},
  url       = {https://mlanthology.org/cvpr/2001/morris2001cvpr-gauge/}
}