Cross-Scale Cost Aggregation for Stereo Matching (CVPR 2014)
================
## Compilation
### Windows
The code is a Visual Studio 2010 project on Windows x64 platform. To build the project, you need to configure [OpenCV](http://opencv.org/) on your own PC. (version 2.4.6, however, other versions are acceptable by modifying [CommFunc.h](/SSCA/CommFunc.h)).
### Other Platforms
The code requires no platform-dependent libraries. Thus, it is easy to compile it on other platforms with OpenCV.
## Usage
Run the program with the following paramters:
`Usage: [CC_METHOD] [CA_METHOD] [PP_METHOD] [C_ALPHA] [lImg] [rImg] [lDis] [maxDis] [disSc]`
- `[CC_METHOD]` -- cost computation methods, currently support:
- `GRD` -- [intensity + gradient](#GF)
- `CEN` -- [Census Transform](#CT)
- `CG` -- Census + gradient
- `[CA_METHOD]` -- cost aggregation methods, currently support:
- `GF` -- [guided image filter](#GF)
- `BF` -- [bilateral filter](#BF)
- `BOX` -- box filter
- `NL` -- [non-local cost aggregation](#NL)
- `ST` -- [segment-tree cost aggregation](#ST)
- `[PP_METHOD]` -- post processing methods, currently support:
- `WM` -- [weighted median filtering](#GF)
- `SG` -- segment based (experimental)
- `[C_ALPHA]` -- regularization paramter, i.e. `$\lambda$` in the paper.
- `[lImg]` -- input left color image file name. (all formats supported by OpenCV)
- `[rImg]` -- input right color image file name.
- `[lDis]` -- output left disparity map file name.
- `[maxDis]` -- maximum disparity range, e.g. `60` for Middlebury and `256` for KITTI dataets.
- `[disSc]` -- scale disparity, e.g. `4` for Middlebury and `1` for KITTI datasets.
**Hint**: to enable post-processing, you must uncomment `// #define COMPUTE_RIGHT` in [CommFunc.h](/SSCA/CommFunc.h) to allow computing right disparity map.
## Citation
Citation is very important for researchers. If you find this code useful, please cite:
```
@inproceedings{CrossScaleStereo,
author = {Kang Zhang and Yuqiang Fang and Dongbo Min and Lifeng Sun and Shiqiang Yang and Shuicheng Yan and Qi Tian},
title = {Cross-Scale Cost Aggregation for Stereo Matching},
booktitle = {CVPR},
year = {2014}
}
```
Since some cost aggregation methods ([GF](#GF), [NL](#NL), [ST](#ST)) are built uppon other papers' code, you also need to cite corresponding papers as listed below.
## Reference
<a name="CT">[CT]</a>: R. Zabih and J. Woodfill. Non-parametric local transforms for computing visual correspondence. In ECCV, 1994
<a name="GF">[GF]</a>: C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. In CVPR, 2011
<a name="ST">[ST]</a>: X. Mei, X. Sun, W. Dong, H. Wang, and X. Zhang. Segment-tree based cost aggregation for stereo matching. In CVPR, 2013
<a name="BF">[BF]</a>: K.-J. Yoon and I. S. Kweon. Adaptive support-weight approach for correspondence search. TPAMI, 2006
<a name="NL">[NL]</a>: Q. Yang. A non-local cost aggregation method for stereo matching. In CVPR, 2012
没有合适的资源?快使用搜索试试~ 我知道了~
资源推荐
资源详情
资源评论
收起资源包目录
CrossScaleStereo-master.zip (71个子文件)
CrossScaleStereo-master
LICENSE 18KB
SSCA.sln 1KB
.tfignore 5B
SSCA
SSCA.vcxproj 10KB
CAFilter
GuidedFilter.h 895B
BilateralFilter.h 181B
GFCA.h 331B
BFCA.h 340B
GFCA.cpp 277B
BoxCA.cpp 295B
BoxCA.h 331B
BilateralFilter.cpp 3KB
GuidedFilter.cpp 8KB
BFCA.cpp 324B
CCMethod.h 709B
PPMethod.h 695B
CAST
segment-graph.h 2KB
StereoDisparity.h 4KB
STCA.cpp 2KB
STCA.h 420B
StereoDisparity.cpp 6KB
ctmf.c 15KB
StereoHelper.cpp 8KB
SegmentTree.h 3KB
SegmentTree.cpp 7KB
disjoint-set.h 2KB
ctmf.h 1KB
Toolkit.cpp 2KB
Toolkit.h 4KB
StereoHelper.h 2KB
GetMehod.h 1KB
CC
GrdCC.cpp 4KB
CGCC.h 626B
CenCC.cpp 4KB
CenCC.h 484B
CGCC.cpp 5KB
GrdCC.h 553B
SSCA.h 1KB
CAMethod.h 586B
CommFunc.h 2KB
PPWM
WMPP.cpp 9KB
WMPP.h 433B
main.cpp 13KB
SSCA.vcxproj.filters 7KB
PPSG
SGPP.cpp 19KB
segment-graph.h 2KB
imconv.h 5KB
convolve.h 2KB
imutil.h 2KB
misc.h 2KB
SGPP.h 618B
filter.h 3KB
disjoint-set.h 2KB
pnmfile.h 5KB
segment-image.h 4KB
image.h 2KB
SSCA.cpp 11KB
CANLC
NLCCA.cpp 2KB
qx_basic.h 13KB
qx_nonlocal_cost_aggregation.cpp 8KB
qx_mst_kruskals_image.cpp 9KB
qx_mst_kruskals_image.h 2KB
qx_nonlocal_cost_aggregation.h 2KB
qx_tree_filter.h 1KB
NLCCA.h 415B
ctmf.c 15KB
ctmf.h 265B
qx_tree_filter.cpp 4KB
qx_basic.cpp 17KB
.gitignore 2KB
README.md 3KB
共 71 条
- 1
资源评论
旅行在明天之前昨天之后
- 粉丝: 10
- 资源: 20
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功