ML Anthology

Edge Descriptors for Robust Wide-Baseline Correspondence

Jason Meltzer, Stefano Soatto
CVPR 2008
doi:10.1109/CVPR.2008.4587684 /cvpr/2008/meltzer2008cvpr-edge/

Abstract

This paper describes a method for finding wide-baseline correspondences between images at locations along gradient edges. We find edges in scale space using established methods and develop invariant descriptors for these edges based on orientation and scale histograms. Because edges are often found on occluding boundaries, we calculate and store two descriptors per edge, one on each side, for robustness to occlusions. We demonstrate the effectiveness of edge matching in the applications of wide-baseline correspondence, structure from motion from line segments, and object category recognition on the Caltech 101 dataset.

PDF CVPR Semantic Scholar

Cite

Text

Meltzer and Soatto. "Edge Descriptors for Robust Wide-Baseline Correspondence." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008. doi:10.1109/CVPR.2008.4587684

Markdown

[Meltzer and Soatto. "Edge Descriptors for Robust Wide-Baseline Correspondence." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008.](https://mlanthology.org/cvpr/2008/meltzer2008cvpr-edge/) doi:10.1109/CVPR.2008.4587684

BibTeX

@inproceedings{meltzer2008cvpr-edge,
  title     = {{Edge Descriptors for Robust Wide-Baseline Correspondence}},
  author    = {Meltzer, Jason and Soatto, Stefano},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2008},
  doi       = {10.1109/CVPR.2008.4587684},
  url       = {https://mlanthology.org/cvpr/2008/meltzer2008cvpr-edge/}
}