计算机科学 ›› 2019, Vol. 46 ›› Issue (8): 303-309.doi: 10.11896/j.issn.1002-137X.2019.08.050

• 图形图像与模式识别 • 上一篇    下一篇

时空约束下的三维动态模型一致性对应

程志豪, 潘翔, 郑河荣   

  1. (浙江工业大学计算机科学与技术学院 杭州310023)
  • 收稿日期:2018-07-02 出版日期:2019-08-15 发布日期:2019-08-15
  • 通讯作者: 郑河荣,男,教授,硕士生导师,主要研究方向为计算机图形学,E-mail:hailiang@zjut.edu.cn
  • 作者简介:程志豪男,硕士生,主要研究方向为计算机图形学;潘翔男,教授,博士生导师,主要研究方向为计算机图形学
  • 基金资助:
    浙江省文物局项目(2014014)

Consistent Correspondence of 3D Dynamic Surface Based on Space-Time Constraints

CHENG Zhi-hao, PAN Xiang, ZHENG He-rong   

  1. (College of Computer Science & Technology,Zhejiang University of Technology,Hangzhou 310023,China)
  • Received:2018-07-02 Online:2019-08-15 Published:2019-08-15

摘要: 已有对应算法由于局部几何特征不稳定而存在错误映射。文中针对三维动态数据,提出了时空约束下的一致性对应算法。首先,算法以相邻帧数据的时空一致性为约束条件,结合非刚性变形理论构建能量最小化方程。其次,通过能量方程约束求解得到稀疏对应关系。最后,针对变形跟踪所导致的对应丢失问题,所提算法结合曲面采样和等距映射完成紧密对应。针对不同的三维动态数据进行实验分析和量化比较,结果所提算法明显优于类似的算法。

关键词: 等距映射, 模型变形, 三维动态数据对应, 时空约束

Abstract: Existing corresponding algorithms will cause error mappings since geometric signatures can’t remain stable and highly similar under different poses.This paper focused on corresponding 3D dynamic surface based on space-time constraints.Firstly,this algorithm constructs the energy optimization function according to the non-rigid deformation model.Secondly,sparse correspondence is computed by optimizing the energy function.Finally,this algorithm of surface sampling and isometric mapping is used to solve the dense matching problem.In experimental part,the analysis and quantification of different 3D motions are carried out,and it turns out that this algorithm can improve the correspondence accuracy.

Key words: 3D dynamic surface correspondence, Isometric mapping, Non-rigid deformation model, Space-time constraints

中图分类号: 

  • TP391
[1]VAN KAICK O,ZHANG H,HAMARNEH G,et al.A Survey on Shape Correspondence[J].Computer Graphics Forum,2011,30(6):1681-1707.
[2]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 &Image Understanding,2013,117(2):158-169.
[3]KUANG Z Z,LI Z M,TIAN W W,et al.Modal Heat Feature and Non-rigid 3D Model Retrieval[J].Journal of Computer-Aided Design & Computer Graphics,2015,27(8):1426-1433.(in Chinese) 匡振中,李宗民,田伟伟,等.热模态特征与非刚体模型检索[J].计算机辅助设计与图形学学报,2015,27(8):1426-1433.
[4]BOSCAINI D,MASCI J,RODOLÀ E,et al.Anisotropic Diffusion Descriptors[J].Computer Graphics Forum,2016,35(2):431-441.
[5]LI N,WANG S,ZHONG M,et al.Generalized Local-to-global Shape Feature Detection based on Graph Wavelets[J].IEEE Transactions on Visualization & Computer Graphics,2015,22(9):1-1.
[6]SAHILLIOGˇLU Y,YEMEZ Y.Partial 3-D Correspondence from Shape Extremities[J].Computer Graphics Forum,2015,33(6):63-76.
[7]WANG J R,FENG J Q,MIAO Y W.Shape Sparse Correspondence for Nearly-Isometric Meshes Based on Green’s Function Representation[J].Journal of Computer-Aided Design & Computer Graphics,2013,25(5):714-723.(in Chinese) 王金荣,冯结青,缪永伟.基于格林函数表示的近似等距网格之间稀疏对应[J].计算机辅助设计与图形学学报,2013,25(5):714-723.
[8]BOSCAINI D,MASCI J,MELZI S,et al.Learning class-specific descriptors for deformable shapes using localized spectral convolutional networks[C]∥Eurographics Symposium on Geometry Processing.Graz:Eurographics Association,2015:13-23.
[9]FANG Y,XIE J,DAI G,et al.3D deep shape descriptor[C]∥ IEEE Conference on Computer Vision and Pattern Recognition.Boston:IEEE Computer Society,2015:2319-2328.
[10]BU S,HAN P,LIU Z,et al.Local deep feature learning framework for 3D shape[J].Computers & Graphics,2015,46:117-129.
[11]LI C,STEVENS A,CHEN C,et al.Learning Weight Uncertainty with Stochastic Gradient MCMC for Shape Classification[C]∥IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE,2016:5666-5675.
[12]HUANG Q X,LEONIDAS G.Consistent Shape Maps via Semidefinite Programming[J].Computer Graphics Forum,2013,32(5):177-186.
[13]COSMO L,RODOLÀ E,ALBARELLI A,et al.Consistent Partial Matching of Shape Collections via Sparse Modeling[J].Computer Graphics Forum,2017,36(1):209-221.
[14]ALHASHIM I,XU K,ZHUANG Y,et al.Deformation-driven topology-varying 3D shape correspondence[J].ACM Transactions on Graphics,2015,34(6):1-13.
[15]GUO K,XU F,WANG Y,et al.Robust Non-rigid Motion Tracking and Surface Reconstruction Using L0 Regularization[C]∥IEEE International Conference on Computer Vision.Santiago:IEEE,2015:3083-3091.
[16]SUMNER R W,SCHMID J,PAULY M.Embedded deformation for shape manipulation[J].ACM Transactions on Graph,2007,26(3):80-87.
[17]PAN X,WANG X C,ZHANG S Y.3D Partial Correspondence Based on Isometric Bipartite Graph[J].Journal of Computer-Aided Design & Computer Graphics,2016,28(3):480-487.(in Chinese) 潘翔,王学成,张三元.基于等距二分图的三维模型局部对齐[J].计算机辅助设计与图形学学报,2016,28(3):480-487.
[18]BRONSTEIN A M,BRONSTEIN M M,KIMMEL R.Efficient computation of isometry-invariant distances between surfaces[J].Siam Journal on Scientific Computing,2006,28(5):1812-1836.
[19]STARCK J,HILTON A.Surface capture for performance-based animation[J].IEEE Computer Graphics & Applications,2007,27(3):21-31.
[20]MADSEN K,NIELSEN H,TINGLEFF O.Methods for Non- Linear Least Squares Problems[M].Denmark:Technical University of Denmark,2004:50-60.
[21]BOGO F,ROMERO J,PONSMOLL G,et al.Dynamic FAUST:Registering Human Bodies in Motion[C]∥IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE,2017:5573-5582.
[1] 郑磊, 吴俊威, 林俊勉, 潘翔.
交互标记约束的三维网格序列分割
Marker-constrained Interactive Segmentation of 3D Animated Meshes
计算机科学, 2020, 47(11A): 271-275. https://doi.org/10.11896/jsjkx.200400030
[2] 张绍群.
基于紧集子覆盖的流形学习算法
Manifold Learning Algorithm Based on Compact Setsub-coverage
计算机科学, 2017, 44(Z6): 88-91. https://doi.org/10.11896/j.issn.1002-137X.2017.6A.018
[3] 范艳芳.
协作环境下的时空约束强制访问控制模型
Temporal-Spatial-based Mandatory Access Control Model in Collaborative Environment
计算机科学, 2017, 44(8): 107-114. https://doi.org/10.11896/j.issn.1002-137X.2017.08.020
[4] 夏英,张俊,王国胤.
时空关联规则挖掘算法及其在ITS中的应用
Spatio-temporal Association Rule Mining Algorithm and its Application in Intelligent Transportation System
计算机科学, 2011, 38(9): 173-176.
[5] .
流形学习方法中的若干问题分析

计算机科学, 2009, 36(4): 25-28.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!