A Global Sampling Method for Alpha Matting

Alpha matting refers to the problem of softly extracting the foreground from an image. Given a trimap (specifying known foreground/background and unknown pixels), a straightforward way to compute the alpha value is to sample some known foreground and background colors for each unknown pixel. Existing sampling-based matting methods often collect samples near the unknown pixels only. They fail if good samples cannot be found nearby. In this paper, we propose a global sampling method that uses all samples available in the image. Our global sample set avoids missing good samples. A simple but effective cost function is defined to tackle the ambiguity in the sample selection process. To handle the computational complexity introduced by the large number of samples, we pose the sampling task as a correspondence problem. The correspondence search is efficiently achieved by generalizing a randomized algorithm previously designed for patch matching[3]. A variety of experiments show that our g...

• Type: Journal
• Year: 2011
• Where: CVPR
• Authors: Kaiming He, Christoph Rhemann, Carsten Rother, Xiaoou Tang, Jian Sun
• Keywords: Computer Vision, CVPR 2011, Global Sampling Method, Matting, Sampling-based Matting Methods