Defocus Matting on Background Blur Priors
Abstract: In this paper, we present a matting method based on focused foreground and blurred background. We classify some pixels as priors to prevent the similarities between foreground and background colors. Firstly, we design a three-channel edge detector to roughly predict some edge pixels. Secondly, for each edge pixel, we estimate its blur degree by fitting an ideal second derivative filter response on the actual one along the gradient direction, and comparing its color and known foreground one. Thirdly, if this pixel is classified into a blurred background edge, we extend it along the gradient direction as blur priors according to the fitting errors to an ideal blurred edge. Finally, with the back-ground blur priors, we run a general matting algorithm along with a trimap expansion method. The experimental results show that our background blur priors could generate much more precise alpha results than the state-of-art algorithms.
文章引用: 姚桂林 , 姚鸿勋 (2012) 基于背景先验点的虚焦抠图方法。 人工智能与机器人研究， 1， 6-14. doi: 10.12677/AIRR.2012.11002
 A. R. Smith, J. F. Blinn. Blue screen matting. ACM Transactions on Graphics (TOG), 1996: 259-268.
 J. Sun, Y. Li, S. B. Kang and H.-Y. Shum. Flash matting. ACM Transactions on Graphics (TOG), 2006, 25(3): 772-778.
 J. Wang, M. Cohen. Simultaneous matting and compositing. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2007.
 N. Joshi, W. Matusik and S. Avidan. Natural video matting using camera arrays. ACM Transactions on Graphics (TOG), 2006: 779-786.
 M. McGuire, W. Matusik, H. Pfister, J. F. Hughes and F. Durand. Defocus video matting. ACM Transactions on Graphics (TOG), 2005: 567-576.
 C. Rhemann, C. Rother, P. Kohli and M. Gelautz. A spatially varying psf-based prior for Alpha matting. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010: 2149- 2156.
 J. Elder, S. Zucker. Local scale control for edge detection and blur estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 1998, 20(7): 699-716.
 S. Bae, F. Durand. Defocus magnification. Proceedings of Eurographics, 2007.
 G. L. Yao, H. X. Yao. Trimap expansion based Alpha matting via localized windows. Technical Re-port, 2012.
 J. Wang, M. Cohen. Optimized color sampling for robust mat- ting. IEEE Conference on Computer Vision and Pattern Recog- nition (CVPR), 2007: 1-8.
 C. Rhemann, C. Rother and M. Gelautz. Improving color modeling for alpha matting. Proceedings of British Machine Vision Conference (BMVC), 2009: 1155-1164.
 C. Rhemann, C. Rother, J. Wang, M. Gelautz, P. Kohli and P. Rott. A perceptually motivated online benchmark for image matting. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009: 1826-1833.
 Z. P. Zhang, Q. S. Zhu and Y. Q. Xie. Learning based Alpha mat- ting using support vector regression. IEEE International Confer- ence on Imaging Processing (ICIP), 2012.
 E. Gastal, M. Oliveira. Shared sampling for real time alpha matting. Proceedings of Eurographics, 2010, 29(2): 575-584.
 K. He, C. Rhemann, C. Rother, X. Tang and J. Sun. A global sampling method for alpha matting. IEEE Conference on Com- puter Vision and Pattern Recognition (CVPR), 2011: 2049-2056.
 A. Levin, D. Lischinski and Y. Weiss. A closed-form solution to natural image matting. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2007, 30(1): 228-242.