文件列表:

LICENSE (16725, 2017-07-21)
install.sh (495, 2017-07-21)
src (0, 2017-07-21)
src\knn_matting.m (1470, 2017-07-21)
src\knn_matting_scribble_hsv.m (1189, 2017-07-21)
src\knn_matting_scribble_rgb.m (1033, 2017-07-21)
src\knn_matting_user_input_brdf.m (1962, 2017-07-21)
src\knn_matting_user_input_image.m (1980, 2017-07-21)
src\run_demo.m (373, 2017-07-21)

# [KNN Matting](http://dingzeyu.li/projects/knn/) Qifeng Chen, Dingzeyu Li, Chi-Keung Tang
The Hong Kong University of Science and Technology
CVPR 2012 / TPAMI 2013 [](http://dingzeyu.li/projects/knn/) ## Installation Steps ### Linux and Mac run "bash install.sh" to download all the required libraries and data. It would take several minutes to tens of minutes, depending on the network connection. ### Windows or Manual Installation - Download the [VLFeat library](http://www.vlfeat.org/download/vlfeat-0.9.20-bin.tar.gz "VLFeat library") and extract into the same directory. - Download the training dataset from [AlphaMatting.com](http://alphamatting.com/datasets.php "Data from Alphamatting.com") . - Extract corresponding files into ${KNN\_MATTING\_DIR}/vlfeat/ and ${KNN\_MATTING\_DIR}/data/, for details please see the ${KNN\_MATTING\_DIR}/src/run_demo.m. ### Optional Data - [SVBRDF data](http://ist.cs.princeton.edu/) from Jason Lawence, the inverse shaded tree database. ## Running the Demo We have been running our codes since Matlab R2011b. The latest version of code is tested on Matlab R2015a. Please let us know if you run into problem. The input method 1.Left click on each layer (Press Space to seperate layers) 2.press Enter to terminate Parameters to change are input at the begining of the code lambda: see equ(12) level: the degree of spatial coherence. normally between 0.5 and 3 factor: the degree of hue. normally between 0.5 and 3 im: an image or BRDF data scrib: scribble l: input windows size is (l*2+1)^2 nn: the number of neighbors. It can be a vector of two elements. For example [10;2] means 10 neighbors with default(level) spatial coherence and 2 neighbors with weak spatial coherence. Note: Scribble inputs in RGB space usually perform better than HSV space. ### More Information For more information, please go to our project site for the detailed paper. ### 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 [Qifeng Chen](http://web.stanford.edu/~cqf/) (cqf@stanford.edu) and [Dingzeyu Li](http://dingzeyu.li/) (dli@cs.columbia.edu)

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：