Bayesian Structure from Motion

Forsyth, David A.; Ioffe, Sergey; Haddon, John A.

doi:10.1109/ICCV.1999.791288

Bayesian Structure from Motion

David A. Forsyth, Sergey Ioffe, John A. Haddon

ICCV 1999 pp. 660-665

doi:10.1109/ICCV.1999.791288 /iccv/1999/forsyth1999iccv-bayesian/

Abstract

Formulates structure from motion as a Bayesian inference problem and uses a Markov-chain Monte Carlo sampler to sample the posterior on this problem. This results in a method that can identify both small and large tracker errors and yields reconstructions that are stable in the presence of these errors. Furthermore, the method gives detailed information on the range of ambiguities in structure given a particular data set and requires no special geometric formulation to cope with degenerate situations. Motion segmentation is obtained by a layer of discrete variables associating a point with an object. We demonstrate a sampler that successfully samples an approximation to the marginal on this domain, producing a relatively unambiguous segmentation.

ICCV Semantic Scholar

Cite

Text

Forsyth et al. "Bayesian Structure from Motion." IEEE/CVF International Conference on Computer Vision, 1999. doi:10.1109/ICCV.1999.791288

Markdown

[Forsyth et al. "Bayesian Structure from Motion." IEEE/CVF International Conference on Computer Vision, 1999.](https://mlanthology.org/iccv/1999/forsyth1999iccv-bayesian/) doi:10.1109/ICCV.1999.791288

BibTeX

@inproceedings{forsyth1999iccv-bayesian,
  title     = {{Bayesian Structure from Motion}},
  author    = {Forsyth, David A. and Ioffe, Sergey and Haddon, John A.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1999},
  pages     = {660-665},
  doi       = {10.1109/ICCV.1999.791288},
  url       = {https://mlanthology.org/iccv/1999/forsyth1999iccv-bayesian/}
}