Robust Point Matching源代码(RPM),matlab2021a测试。

上传者: ccsss22 | 上传时间: 2022-05-01 21:06:30 | 文件大小: 34KB | 文件类型: RAR
ICP算法通过迭代的方式解决点云的刚性配准: (1) 基于最近空间距离寻找hard的点对应关系; (2) 求解最小二乘变换。其中第(1)步对待配准点云的初始位置和噪声点/离群点敏感,会导致迭代收敛到错误的局部最小值。在本文中,作者提出了RPM-Net,一种对初始化不太敏感且鲁棒的、基于学习的用于刚性点云配准方法。为此,RMP-Net使用可微的Sinkhorn层和退火(Annealing)技术,利用从空间坐标和局部几何信息中学习到的混合特征,实现点对应(point correspondences)的软(soft)分配。为了提高配准性能,作者引入了第二个网络来预测最佳退火参数。与现有的一些方法不同,RPM-Net可以处理部分可见和丢失correspondences的点云。实验结果表明,与现有的非深度学习和最近的基于深度学习的方法相比,RPM-Net达到了SOTA。

文件下载

资源详情

[{"title":"( 29 个子文件 34KB ) Robust Point Matching源代码(RPM),matlab2021a测试。","children":[{"title":"TPS-RPM","children":[{"title":"ctps_gen.m <span style='color:#111;'> 5.08KB </span>","children":null,"spread":false},{"title":"cMIX_calc_m_ICP.m <span style='color:#111;'> 3.32KB </span>","children":null,"spread":false},{"title":"figb.m <span style='color:#111;'> 721B </span>","children":null,"spread":false},{"title":"cplotg.m <span style='color:#111;'> 2.90KB </span>","children":null,"spread":false},{"title":"ctps_plot_grid_gen1.m <span style='color:#111;'> 2.91KB </span>","children":null,"spread":false},{"title":"fig.m <span style='color:#111;'> 692B </span>","children":null,"spread":false},{"title":"cICP_findneighbours.m <span style='color:#111;'> 2.08KB </span>","children":null,"spread":false},{"title":"crbf_plot_grid.m <span style='color:#111;'> 1.35KB </span>","children":null,"spread":false},{"title":"demodata_ex4.mat <span style='color:#111;'> 3.30KB </span>","children":null,"spread":false},{"title":"ctps_plot_gridbox.m <span style='color:#111;'> 1.89KB </span>","children":null,"spread":false},{"title":"ctps_plot_grid_gen.m <span style='color:#111;'> 3.61KB </span>","children":null,"spread":false},{"title":"cMIX_plot_simple.m <span style='color:#111;'> 7.29KB </span>","children":null,"spread":false},{"title":"ctps_plot_grid.m <span style='color:#111;'> 2.41KB </span>","children":null,"spread":false},{"title":"ctps_warp_pts.m <span style='color:#111;'> 2.00KB </span>","children":null,"spread":false},{"title":"demodata_ex3.mat <span style='color:#111;'> 1.80KB </span>","children":null,"spread":false},{"title":"cMIX_plot_mixture_simple.m <span style='color:#111;'> 1.90KB </span>","children":null,"spread":false},{"title":"runme.m <span style='color:#111;'> 5.71KB </span>","children":null,"spread":false},{"title":"cMIX_warp_pts.m <span style='color:#111;'> 1.03KB </span>","children":null,"spread":false},{"title":"cpause.m <span style='color:#111;'> 956B </span>","children":null,"spread":false},{"title":"demodata_ex1.mat <span style='color:#111;'> 2.11KB </span>","children":null,"spread":false},{"title":"demodata_ex2.mat <span style='color:#111;'> 1.80KB </span>","children":null,"spread":false},{"title":"cMIX_normalize_m.m <span style='color:#111;'> 1.72KB </span>","children":null,"spread":false},{"title":"crbf_gen.m <span style='color:#111;'> 3.24KB </span>","children":null,"spread":false},{"title":"cplot.m <span style='color:#111;'> 2.85KB </span>","children":null,"spread":false},{"title":"cMIX_calc_transformation.m <span style='color:#111;'> 1.26KB </span>","children":null,"spread":false},{"title":"crbf_warp_pts.m <span style='color:#111;'> 964B </span>","children":null,"spread":false},{"title":"cMIX.m <span style='color:#111;'> 11.11KB </span>","children":null,"spread":false},{"title":"demodata_ex5.mat <span style='color:#111;'> 3.52KB </span>","children":null,"spread":false}],"spread":false},{"title":"fpga&matlab.txt <span style='color:#111;'> 17B </span>","children":null,"spread":false}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明