Parallel and Distributed Graph Cuts VideoLectures并行和分布式图形切割 videolectures.net.pptVIP

下载本文档

1
0
约2.4千字
约 19页
2017-03-08 发布于上海
举报
版权申诉

Parallel and Distributed Graph Cuts VideoLectures并行和分布式图形切割 videolectures.net.ppt

1、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
7、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

Parallel and Distributed Graph Cuts VideoLectures并行和分布式图形切割 videolectures.net

* * * * * * * * * * * * * Petter Strandmark Fredrik Kahl Lund University Image denoising Stereo estimation Segmentation Shape fitting from point clouds S T 2 1 1 3 1 1 3 1 2 1 3 2 1 1 2 1 5 2 1 1 4 2 3 1 1 2 2 1 1 Minimum cut: 4 1 1 Delong and Boykov, CVPR 2008 Implementation of push-relabel Excellent speed-up for 2-8 processors Method of choice for dense 3D graphs CUDA-cuts: Vineet and Narayanan, CVGPU CVPR 2008 Push-relabel on GPU Not clear what range of regularization can be used L1-norm: Bhusnurmath and Taylor, PAMI 2008 Solves continuous problem on GPU Not faster than augmenting paths on single processor Liu and Sun, CVPR 2010 ” Parallel Graph-cuts by Adaptive Bottom-up Merging” Splits large graph into several pieces Augmenting paths found separately Pieces merged together and search trees reused Our approach Graph split into several pieces Solutions constrained to be equal with dual variables Shared memory not required See Komodakis et al. in ICCV 2007 for dual decomposition Two separate problems! Dualize the constraint! = = = ≠ 3 1 1 3 1 1 4 2 3 1 2 1 1 3 4 2 3 1 2 1 3 2 1 1 2 1 2 1 1 1 2 3 1 3 S T ? ? Zero duality gap Dual function has a maximum such that the constraints are met Global solution guaranteed! Original Min-cut Problem Decomposed Min-cut Problem ? ? Linear Program ? Dual Linear Program Decomposed Linear Program ? Theorem: If the graph weights are even integers, there exists an integer vector maximizing the dual function. This means that the dual problem can be solved without floating point arithmetic. Begin with a graph Split into two parts Constrained to be equalon the overlap - 1 2 3 = Independent problems! Berkeley segmentation database 301 images 2 processors 4 processors Iteration 1 2 3 4 5 ... 10 11 Differences 108 105 30 33 16 ... 9 0 Time (ms) 245 1.5 1.2 0.1 0.08 ... 0.07 0.47 1152 × 1536 Easy problem: 230 ms Hard problem: 4 s S T This choice of split severes all possible s/t paths Parallel approach still 30% faster LUNARC clu