ML Anthology

Alpha Estimation in Natural Images

Mark A. Ruzon, Carlo Tomasi
CVPR 2000 pp. 1018-1025
doi:10.1109/CVPR.2000.855793 /cvpr/2000/ruzon2000cvpr-alpha/

Abstract

Many boundaries between objects in the world project onto curves in an image. However, boundaries involving natural objects (e.g., trees, hair, water, smoke) are often unworkable under this model because many pixels receive light from more than one object. We propose a technique for estimating alpha, the proportion in which two colors mix to produce a color at the boundary. The technique extends blue screen matting to backgrounds that have almost arbitrary color distributions, though coarse knowledge of the boundary's location is required. Results show a number of different objects moved from one image to another while maintaining naturalism.

CVPR Semantic Scholar

Cite

Text

Ruzon and Tomasi. "Alpha Estimation in Natural Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000. doi:10.1109/CVPR.2000.855793

Markdown

[Ruzon and Tomasi. "Alpha Estimation in Natural Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000.](https://mlanthology.org/cvpr/2000/ruzon2000cvpr-alpha/) doi:10.1109/CVPR.2000.855793

BibTeX

@inproceedings{ruzon2000cvpr-alpha,
  title     = {{Alpha Estimation in Natural Images}},
  author    = {Ruzon, Mark A. and Tomasi, Carlo},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2000},
  pages     = {1018-1025},
  doi       = {10.1109/CVPR.2000.855793},
  url       = {https://mlanthology.org/cvpr/2000/ruzon2000cvpr-alpha/}
}