ML Anthology

High Resolution Matting via Interactive Trimap Segmentation

Christoph Rhemann, Carsten Rother, Alex Rav-Acha, Toby Sharp
CVPR 2008
doi:10.1109/CVPR.2008.4587441 /cvpr/2008/rhemann2008cvpr-high/

Abstract

We present a new approach to the matting problem which splits the task into two steps: interactive trimap extraction followed by trimap-based alpha matting. By doing so we gain considerably in terms of speed and quality and are able to deal with high resolution images. This paper has three contributions: (i) a new trimap segmentation method using parametric max-flow; (ii) an alpha matting technique for high resolution images with a new gradient preserving prior on alpha; (iii) a database of 27 ground truth alpha mattes of still objects, which is considerably larger than previous databases and also of higher quality. The database is used to train our system and to validate that both our trimap extraction and our matting method improve on state-of-the-art techniques.

CVPR Semantic Scholar

Cite

Text

Rhemann et al. "High Resolution Matting via Interactive Trimap Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008. doi:10.1109/CVPR.2008.4587441

Markdown

[Rhemann et al. "High Resolution Matting via Interactive Trimap Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008.](https://mlanthology.org/cvpr/2008/rhemann2008cvpr-high/) doi:10.1109/CVPR.2008.4587441

BibTeX

@inproceedings{rhemann2008cvpr-high,
  title     = {{High Resolution Matting via Interactive Trimap Segmentation}},
  author    = {Rhemann, Christoph and Rother, Carsten and Rav-Acha, Alex and Sharp, Toby},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2008},
  doi       = {10.1109/CVPR.2008.4587441},
  url       = {https://mlanthology.org/cvpr/2008/rhemann2008cvpr-high/}
}