ML Anthology

Nonlocal Matting

Philip Greggory Lee, Ying Wu
CVPR 2011 pp. 2193-2200
doi:10.1109/CVPR.2011.5995665 /cvpr/2011/lee2011cvpr-nonlocal/

Abstract

This work attempts to considerably reduce the amount of user effort in the natural image matting problem. The key observation is that the nonlocal principle, introduced to denoise images, can be successfully applied to the alpha matte to obtain sparsity in matte representation, and therefore dramatically reduce the number of pixels a user needs to manually label. We show how to avoid making the user provide redundant and unnecessary input, develop a method for clustering the image pixels for the user to label, and a method to perform high-quality matte extraction. We show that this algorithm is therefore faster, easier, and higher quality than state of the art methods.

CVPR Semantic Scholar

Cite

Text

Lee and Wu. "Nonlocal Matting." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995665

Markdown

[Lee and Wu. "Nonlocal Matting." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/lee2011cvpr-nonlocal/) doi:10.1109/CVPR.2011.5995665

BibTeX

@inproceedings{lee2011cvpr-nonlocal,
  title     = {{Nonlocal Matting}},
  author    = {Lee, Philip Greggory and Wu, Ying},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {2193-2200},
  doi       = {10.1109/CVPR.2011.5995665},
  url       = {https://mlanthology.org/cvpr/2011/lee2011cvpr-nonlocal/}
}