Spectral Matting

Anat Levin, Alex Rav-Acha, Dani Lischinski

CVPR 2007

doi:10.1109/CVPR.2007.383147 /cvpr/2007/levin2007cvpr-spectral/

Abstract

We present spectral matting: a new approach to natural image matting that automatically computes a set of fundamental fuzzy matting components from the smallest eigenvectors of a suitably defined Laplacian matrix. Thus, our approach extends spectral segmentation techniques, whose goal is to extract hard segments, to the extraction of soft matting components. These components may then be used as building blocks to easily construct semantically meaningful foreground mattes, either in an unsupervised fashion, or based on a small amount of user input.

CVPR Semantic Scholar

Cite

Text

Levin et al. "Spectral Matting." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007. doi:10.1109/CVPR.2007.383147

Markdown

[Levin et al. "Spectral Matting." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007.](https://mlanthology.org/cvpr/2007/levin2007cvpr-spectral/) doi:10.1109/CVPR.2007.383147

BibTeX

@inproceedings{levin2007cvpr-spectral,
  title     = {{Spectral Matting}},
  author    = {Levin, Anat and Rav-Acha, Alex and Lischinski, Dani},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2007},
  doi       = {10.1109/CVPR.2007.383147},
  url       = {https://mlanthology.org/cvpr/2007/levin2007cvpr-spectral/}
}