bayesian-matting-master
所属分类:其他
开发工具:Python
文件大小:232KB
下载次数:10
上传日期:2017-12-11 15:22:26
上 传 者:
ns5417
说明: 本文将以图像抠图领域的经典算法——贝叶斯抠图(Bayesian Matting)为例来介绍有关图像抠图技术的一些内容。贝叶斯抠图源自文献【2】,是2001年发表在CVPR上的一篇经典论文。
(the image matting using classic bayesian approach)
文件列表:
bayesian_matting.py (7028, 2017-01-24)
gandalf.png (214290, 2017-01-24)
gandalfAlpha.png (8456, 2017-01-24)
gandalfTrimap.png (8458, 2017-01-24)
orchard_bouman_clust.py (1491, 2017-01-24)
# bayesian-matting
Python implementation of Yung-Yu Chuang, Brian Curless, David H. Salesin, and Richard Szeliski. A Bayesian Approach to Digital Matting. In Proceedings of IEEE Computer Vision and Pattern Recognition (CVPR 2001), Vol. II, 2***-271, December 2001
### Requirements
- python 3.5+ (Though it should run on 2.7 with some minor tweaks)
- scipy
- numpy
- numba > 0.30.1 (Not neccesary, but does give a 5x speedup)
- matplotlib
- opencv
### Running the demo
- 'python bayesian_matting.py'
- sigma () fall off of gaussian weighting to local window
- N size of window to construct local fg/bg clusters from
- minN minimum number of known pixels in local window to proceed
### Results
### More Information
For more information see the orginal project website http://grail.cs.washington.edu/projects/digital-matting/image-matting/
This implementation was mostly adapted from Michael Rubinsteins matlab code here,
http://www1.idc.ac.il/toky/CompPhoto-09/Projects/Stud_projects/Miki/index.html
http://people.csail.mit.edu/mrub/code/bayesmat.zip
### Disclaimer
The code is free for academic/research purpose. Use at your own risk and we are not responsible for any loss resulting from this code. Feel free to submit pull request for bug fixes.
### Contact
[Marco Forte](https://marcoforte.github.io/) (fortem@tcd.ie)
#### Original authors:
[Yung-Yu Chuang](http://www.cs.washington.edu/homes/cyy)
[Brian Curless](http://www.cs.washington.edu/homes/curless)
[David Salesin](http://www.cs.washington.edu/homes/salesin)
[Richard Szeliski](http://www.research.microsoft.com/~szeliski)
近期下载者:
相关文件:
收藏者: