Motion-Aware KNN Laplacian for Video Matting

Dingzeyu Li, Qifeng Chen, Chi-Keung Tang; The IEEE International Conference on Computer Vision (ICCV), 2013, pp. 3599-3606

Abstract


This paper demonstrates how the nonlocal principle benefits video matting via the KNN Laplacian, which comes with a straightforward implementation using motionaware K nearest neighbors. In hindsight, the fundamental problem to solve in video matting is to produce spatiotemporally coherent clusters of moving foreground pixels. When used as described, the motion-aware KNN Laplacian is effective in addressing this fundamental problem, as demonstrated by sparse user markups typically on only one frame in a variety of challenging examples featuring ambiguous foreground and background colors, changing topologies with disocclusion, significant illumination changes, fast motion, and motion blur. When working with existing Laplacian-based systems, our Laplacian is expected to benefit them immediately with improved clustering of moving foreground pixels.

Related Material


[pdf]
[bibtex]
@InProceedings{Li_2013_ICCV,
author = {Li, Dingzeyu and Chen, Qifeng and Tang, Chi-Keung},
title = {Motion-Aware KNN Laplacian for Video Matting},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2013}
}