Sciweavers

Share
CVPR
2010
IEEE

Fast Matting Using Large Kernel Matting Laplacian Matrices

11 years 18 days ago
Fast Matting Using Large Kernel Matting Laplacian Matrices
Image matting is of great importance in both computer vision and graphics applications. Most existing state-of-the-art techniques rely on large sparse matrices such as the matting Laplacian [12]. However, solving these linear systems is often time-consuming, which is unfavored for the user interaction. In this paper, we propose a fast method for high quality matting. We first derive an efficient algorithm to solve a large kernel matting Laplacian. A large kernel propagates information more quickly and may improve the matte quality. To further reduce running time, we also use adaptive kernel sizes by a KD-tree trimap segmentation technique. A variety of experiments show that our algorithm provides high quality results and is 5 to 20 times faster than previous methods.
Kaiming He, Jian Sun, Xiaoou Tang
Added 07 Apr 2010
Updated 14 May 2010
Type Conference
Year 2010
Where CVPR
Authors Kaiming He, Jian Sun, Xiaoou Tang
Comments (0)
books