ML Anthology

Branch-and-Bound Hypothesis Selection for Two-View Multiple Structure and Motion Segmentation

Ninad Thakoor, Jean Gao
CVPR 2008
doi:10.1109/CVPR.2008.4587469 /cvpr/2008/thakoor2008cvpr-branch/

Abstract

An efficient and robust framework for two-view multiple structure and motion segmentation is proposed. To handle this otherwise recursive problem, hypotheses for the models are generated by local sampling. Once these hypotheses are available, a model selection problem is formulated which takes into account the hypotheses likelihoods and model complexity. An explicit model for outliers is also added for robust model selection. The model selection criterion is optimized through branch-and-bound technique of combinatorial optimization which guaranties optimality over current set of hypotheses by efficient search of solution space.

CVPR Semantic Scholar

Cite

Text

Thakoor and Gao. "Branch-and-Bound Hypothesis Selection for Two-View Multiple Structure and Motion Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008. doi:10.1109/CVPR.2008.4587469

Markdown

[Thakoor and Gao. "Branch-and-Bound Hypothesis Selection for Two-View Multiple Structure and Motion Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008.](https://mlanthology.org/cvpr/2008/thakoor2008cvpr-branch/) doi:10.1109/CVPR.2008.4587469

BibTeX

@inproceedings{thakoor2008cvpr-branch,
  title     = {{Branch-and-Bound Hypothesis Selection for Two-View Multiple Structure and Motion Segmentation}},
  author    = {Thakoor, Ninad and Gao, Jean},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2008},
  doi       = {10.1109/CVPR.2008.4587469},
  url       = {https://mlanthology.org/cvpr/2008/thakoor2008cvpr-branch/}
}