denseCRF_matlab-master
所属分类：matlab编程
开发工具：matlab
文件大小：15446KB
下载次数：365
上传日期：2016-04-27 22:07:02
上 传 者：
dadalang0511
说明： MIT的nips11文章的matlab实现，全连接crf做图像语义分割示例，代码很清晰，方便自己改进
(matlab implementation of MIT s paper in nips11 articlesFully connected crf do semantic image segmentation example, the code is very clear, easy to improve themselves)
文件列表:
compile.m (153, 2015-11-24)
demo.m (1371, 2015-11-24)
loadTextonboost.m (833, 2015-11-24)
src (0, 2015-11-24)
src\bipartitedensecrf.cpp (7281, 2015-11-24)
src\densecrf.cpp (10408, 2015-11-24)
src\densecrf.h (7710, 2015-11-24)
src\fastmath.h (4197, 2015-11-24)
src\filter.cpp (2589, 2015-11-24)
src\fullCRFinfer.cpp (2236, 2015-11-24)
src\fullCRFinfer.mexa64 (48286, 2015-11-24)
src\permutohedral.cpp (1610, 2015-11-24)
src\permutohedral.h (23244, 2015-11-24)
src\sse_defs.h (2305, 2015-11-24)
src\util.cpp (1955, 2015-11-24)
src\util.h (1890, 2015-11-24)
test.png (779259, 2015-11-24)
test.unary (29646860, 2015-11-24)
This is a MATLAB wrapper for Philipp Krhenbhl's [Fully-Connected CRFs](http://www.philkr.net/home/densecrf).
If you use this code for your reasearch, please cite:
```
Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
Philipp Krhenbhl and Vladlen Koltun
NIPS 2011
```
and provide a link to this repository as a footnote or a citation.
Usage
=======================
In the first stage, run compile.m
A demo.m file is provided along with a binary of trained textonboost unary.
Learning
----------
Please feel free to contact xjsjtu88@gmail.com for any questions or bug reports.
近期下载者：
相关文件：
收藏者：