Analytical Methods for Uncalibrated Stereo and Motion Reconstruction

Abstract

We present a new approach to relative stereo and motion reconstruction from a discrete set of point correspondences in completely uncalibrated pairs of images. This approach also yields new projective invariants, and we present some applications to object recognition. Finally, we introduce a new approach to camera self-calibration from two images which allows full metric reconstruction up to some unknown scale factor. We have implemented the proposed methods and present examples using real images.

Cite

Text

Ponce et al. "Analytical Methods for Uncalibrated Stereo and Motion Reconstruction." European Conference on Computer Vision, 1994. doi:10.1007/3-540-57956-7_51

Markdown

[Ponce et al. "Analytical Methods for Uncalibrated Stereo and Motion Reconstruction." European Conference on Computer Vision, 1994.](https://mlanthology.org/eccv/1994/ponce1994eccv-analytical/) doi:10.1007/3-540-57956-7_51

BibTeX

@inproceedings{ponce1994eccv-analytical,
  title     = {{Analytical Methods for Uncalibrated Stereo and Motion Reconstruction}},
  author    = {Ponce, Jean and Marimont, David H. and Cass, Todd A.},
  booktitle = {European Conference on Computer Vision},
  year      = {1994},
  pages     = {463-470},
  doi       = {10.1007/3-540-57956-7_51},
  url       = {https://mlanthology.org/eccv/1994/ponce1994eccv-analytical/}
}