Moving Forward in Structure from Motion

Andrea Vedaldi, Gregorio Guidi, Stefano Soatto

CVPR 2007

doi:10.1109/CVPR.2007.383117 /cvpr/2007/vedaldi2007cvpr-moving/

Abstract

It is well-known that forward motion induces a large number of local minima in the instantaneous least-squares reprojection error. This is caused in part by singularities in the error landscape around the forward direction, and presents a challenge in using existing algorithms for structure-from-motion in autonomous navigation applications. In this paper we prove that imposing a bound on the reconstructed depth of the scene makes the least-squares re-projection error continuous. This has implications for autonomous navigation, as it suggests simple modifications for existing algorithms to minimize the effects of local minima in forward translation.

CVPR Semantic Scholar

Cite

Text

Vedaldi et al. "Moving Forward in Structure from Motion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007. doi:10.1109/CVPR.2007.383117

Markdown

[Vedaldi et al. "Moving Forward in Structure from Motion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007.](https://mlanthology.org/cvpr/2007/vedaldi2007cvpr-moving/) doi:10.1109/CVPR.2007.383117

BibTeX

@inproceedings{vedaldi2007cvpr-moving,
  title     = {{Moving Forward in Structure from Motion}},
  author    = {Vedaldi, Andrea and Guidi, Gregorio and Soatto, Stefano},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2007},
  doi       = {10.1109/CVPR.2007.383117},
  url       = {https://mlanthology.org/cvpr/2007/vedaldi2007cvpr-moving/}
}