Natural Image Matting
Abstract
Matte pulling - generating greyscale images which indicate segmentation of images into elements with subpixel accuracy and where blur causes pixels to be a mixture of elements - has received attention in recent years. Many of the algorithms are too slow or too unpredictable to be of practical use in motion picture Post-production. Assessing the performance of different algorithms is also a complex task. This paper presents an optimisation which can be applied to many algorithms in order to allow them to run at interactive speeds, introduces a new algorithm based on Colour Lines, and presents a technique which can be used as a formal test-bench to measure the performance of matte algorithms.
BibTeX
@inproceedings {10.2312:vvg.20051029,
booktitle = {Vision, Video, and Graphics (2005)},
editor = {Mike Chantler},
title = {{Natural Image Matting}},
author = {Hillman, Peter M. and Hannah, John M.},
year = {2005},
publisher = {The Eurographics Association},
ISBN = {3-905673-57-6},
DOI = {10.2312/vvg.20051029}
}
booktitle = {Vision, Video, and Graphics (2005)},
editor = {Mike Chantler},
title = {{Natural Image Matting}},
author = {Hillman, Peter M. and Hannah, John M.},
year = {2005},
publisher = {The Eurographics Association},
ISBN = {3-905673-57-6},
DOI = {10.2312/vvg.20051029}
}