结合热核信号和测地距离的三维模型紧密对齐

计算机科学 ›› 2015, Vol. 42 ›› Issue (Z6): 199-202.

结合热核信号和测地距离的三维模型紧密对齐

阮义彰,童伟淮,潘翔,章国栋

浙江工业大学国际学院杭州310023,浙江工业大学计算机科学与技术学院杭州310023,浙江工业大学计算机科学与技术学院杭州310023,浙江工业大学计算机科学与技术学院杭州310023

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受国家自然科学基金(61272304),浙江省文物局项目(2014014)资助

3D Shape Dense Correspondence by Combining Heat Kernel and Geodesic Distance

RUAN Yi-zhang, TONG Wei-huai, PAN Xiang and ZHANG Guo-dong

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 针对测地距离所导致的错误紧密匹配问题,提出了一种结合热核信号和测地距离的三维模型紧密对齐新方法,它可以有效提高对齐准确性。该方法提取特征点的多尺度热核信号,然后以特征点之间的测地距离作为相容性条件,得到可靠稳定的三角匹配。最后在三角匹配的基础上,采用多分辨率方法实现紧密对齐。实验比较分析表明,该方法通过局部几何特征去除误匹配,能够得到更好的对齐结果。

Abstract: This paper addressed the problem about dense correspondence between two 3D deformable shapes.It proposed a new algorithm by combining heat kernel and geodesic distance.It can effectively improve the accuracy of correspondence by taking pose-insensitive character of the kernel signature.The whole algorithm mainly consists of three steps.Firstly,it extracts multi-scale heat kernel for each feature point.Secondly,it finds the triple matching by considering two factors since it builds a triple matching by combining similarity that the algorithm detects the external feature points from input 3D meshes.Secondly,the algorithm uses HKS to define the local feature for external points.Finally,the algorithm searches the best three-point matching by combining local feature descriptor and geodesic distance of external points.In experiment,the proposed algorithm is proven to be very robust in sparse matching for 3D deformable shapes.

Key words: Dense correspondence,Heat kernel,Geodesic distance,Triple matching

阮义彰,童伟淮,潘翔,章国栋. 结合热核信号和测地距离的三维模型紧密对齐[J]. 计算机科学, 2015, 42(Z6): 199-202. https://doi.org/

RUAN Yi-zhang, TONG Wei-huai, PAN Xiang and ZHANG Guo-dong. 3D Shape Dense Correspondence by Combining Heat Kernel and Geodesic Distance[J]. Computer Science, 2015, 42(Z6): 199-202. https://doi.org/

参考文献

[1] Van Kaick O,Zhang H,Hamarneh G,et al.A survey on shape correspondence[J].Computer Graphics Forum,Blackwell Publishing Ltd,2011,30(6):1681-1707
[2] Tam G K L,Cheng Z Q,Lai Y K,et al.Registration of 3D point clouds and meshes:A survey from rigid to nonrigid[J].IEEE Transactions on Visualization and Computer Graphics,2013,19(7):1199-1217
[3] Besl P J,McKay N D.Method for registration of 3-D shapes[C]∥Robotics-DL tentative.International Society for Optics and Photonics.1992:586-606
[4] Rusinkiewicz S,Levoy M.Efficient variants of the ICP algorithm[C]∥Third International Conference on 3-D Digital Imaging and Modeling,2001.IEEE,2001:145-152
[5] 杨棽,齐越,沈旭昆,等.一种快速的三维扫描数据自动配准方法[J].软件学报,2010,21(6):1438-1450
[6] 戴静兰,陈志杨,叶修梓.ICP 算法在点云配准中的应用[J].中国图象图形学报,2007,12(3):517-521
[7] 朱延娟,周来水,张丽艳.散乱点云数据配准算法[J].计算机辅助设计与图形学学报,2006,18(4):475-481
[8] Smeets D,Keustermans J,Vandermeulen D,et al.meshSIFT:Local surface features for 3D face recognition under expression variations and partial data[J].Computer Vision and Image Understanding,2013,117(2):158-169
[9] Tevs A,Bokeloh M,Wand M,et al.Isometric registration of ambiguous and partial data[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2009(CVPR 2009).IEEE,2009:1185-1192
[10] 李俊,程志全,李宏华,等.一种面向大尺度变形的非刚性注册算法[J].计算机学报,2011,34(3):539-547
[11] Sahillioˇlu Y,Yemez Y.Scale normalization for isometric shape matching[J].Computer Graphics Forum,Blackwell Publishing Ltd,2012,31(7):2233-2240
[12] Bronstein A M,Bronstein M M,Kimmel R.Generalized multidimensional scaling:a framework for isometry-invariant partial surface matching[J].Proceedings of the National Academy of Sciences of the United States of America,2006,103(5):1168-1172
[13] Sahillioglu Y,Yemez Y.Minimum-distortion isometric shapecorrespondence using EM algorithm[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11):2203-2215
[14] Sánta Z,Kato Z.Correspondence-Less Non-Rigid Registration of Triangular Surface Meshes[C]∥2013 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2013:2275-2282
[15] Ruggeri M R,Patanè G,Spagnuolo M,et al.Spectral-drivenisometry-invariant matching of 3D shapes[J].International Journal of Computer Vision,2010,89(2/3):248-265
[16] Lipman Y,Funkhouser T.Mbius voting for surface correspondence[J].ACM Transactions on Graphics(TOG),ACM,2009,28(3):72
[17] Kim V G,Lipman Y,Funkhouser T.Blended intrinsic maps[J].ACM Transactions on Graphics(TOG),ACM,2011,30(4):79
[18] Ovsjanikov M,Mérigot Q,Mémoli F,et al.One point isometric matching with the heat kernel[J].Computer Graphics Forum,Blackwell Publishing Ltd,2010,29(5):1555-1564
[19] Ovsjanikov M,Ben-Chen M,Solomon J,et al.Functional maps:a flexible representation of maps between shapes[J].ACM Tran-sactions on Graphics(TOG),2012,31(4):30
[20] Wu H Y,Zha H.Robust consistent correspondence between 3D non-rigid shapes based on “Dual Shape-DNA”[C]∥2011 IEEE International Conference on Computer Vision(ICCV).IEEE,2011:587-594
[21] Pokrass J,Bronstein A M,Bronstein M M,et al.Sparse mode-ling of intrinsic correspondences[J].Computer Graphics Forum,Blackwell Publishing Ltd,2013,32(2pt4):459-468
[22] Agathos A,Pratikakis I,Perantonis S,et al.Protrusion-oriented 3D mesh segmentation[J].The Visual Computer,2010,26(1):63-81

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed