ML Anthology

Structure-and-Motion Pipeline on a Hierarchical Cluster Tree

Michela Farenzena, Andrea Fusiello, Riccardo Gherardi
ICCVW 2009 pp. 1489-1496
doi:10.1109/ICCVW.2009.5457435 /iccvw/2009/farenzena2009iccvw-structureandmotion/

Abstract

This papers introduces a novel hierarchical scheme for computing Structure and Motion. The images are organized into a tree with agglomerative clustering, using a measure of overlap as the distance. The reconstruction follows this tree from the leaves to the root. As a result, the problem is broken into smaller instances, which are then separately solved and combined. Compared to the standard sequential approach, this framework has a lower computational complexity, it is independent from the initial pair of views, and copes better with drift problems. A formal complexity analysis and some experimental results support these claims.

ICCVW Semantic Scholar

Cite

Text

Farenzena et al. "Structure-and-Motion Pipeline on a Hierarchical Cluster Tree." IEEE/CVF International Conference on Computer Vision Workshops, 2009. doi:10.1109/ICCVW.2009.5457435

Markdown

[Farenzena et al. "Structure-and-Motion Pipeline on a Hierarchical Cluster Tree." IEEE/CVF International Conference on Computer Vision Workshops, 2009.](https://mlanthology.org/iccvw/2009/farenzena2009iccvw-structureandmotion/) doi:10.1109/ICCVW.2009.5457435

BibTeX

@inproceedings{farenzena2009iccvw-structureandmotion,
  title     = {{Structure-and-Motion Pipeline on a Hierarchical Cluster Tree}},
  author    = {Farenzena, Michela and Fusiello, Andrea and Gherardi, Riccardo},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2009},
  pages     = {1489-1496},
  doi       = {10.1109/ICCVW.2009.5457435},
  url       = {https://mlanthology.org/iccvw/2009/farenzena2009iccvw-structureandmotion/}
}