ML Anthology

New Algorithms for Two-Frame Structure from Motion

John Oliensis, Yakup Genc
ICCV 1999 pp. 737-744
doi:10.1109/ICCV.1999.790295 /iccv/1999/oliensis1999iccv-new/

Abstract

We describe two new algorithms for two-frame structure from motion from tracked point features. One is the first fast algorithm for computing an exact least-squares estimate. It exploits our observation that the rotationally invariant least-squares error can be written in a simple form that depends just on the motion. The other is essentially as accurate as the least-squares estimate and is more efficient, probably faster, and potentially more robust than previous algorithms of comparable accuracy. We also analyze theoretically the accuracy of the optical-flow approximation to the least-squares error.

ICCV Semantic Scholar

Cite

Text

Oliensis and Genc. "New Algorithms for Two-Frame Structure from Motion." IEEE/CVF International Conference on Computer Vision, 1999. doi:10.1109/ICCV.1999.790295

Markdown

[Oliensis and Genc. "New Algorithms for Two-Frame Structure from Motion." IEEE/CVF International Conference on Computer Vision, 1999.](https://mlanthology.org/iccv/1999/oliensis1999iccv-new/) doi:10.1109/ICCV.1999.790295

BibTeX

@inproceedings{oliensis1999iccv-new,
  title     = {{New Algorithms for Two-Frame Structure from Motion}},
  author    = {Oliensis, John and Genc, Yakup},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1999},
  pages     = {737-744},
  doi       = {10.1109/ICCV.1999.790295},
  url       = {https://mlanthology.org/iccv/1999/oliensis1999iccv-new/}
}