|
|
|
| Spectral graph wavelet descriptor for three-dimensional shape matching |
Ling HU1,2( ),Qin-song LI1,Sheng-jun LIU1,*(),Xin-ru LIU1 |
1. School of Mathematics and Statistics, Central South University, Changsha 410000, China
2. School of Mathematics and Computing, Hunan First Normal College, Changsha 410000, China |
|
|
|
Abstract A point descriptor was proposed based on the spectral graph wavelet transform (SGWT) for the pointwise three-dimensional shape matching. SGWT was performed for a series of impulse functions centered at each point on the shape. Since these wavelet coefficients can reflect sufficient multiscale geometric information around each point, they are orderly treated as elements of a high?dimensional vector. Such vector is the descriptor for each point and the geometric disparity between points can be measured by their Euclidean distance. The spectral graph wavelet (SGW) both use low-pass and band-pass filters to analyze the signals and can stably reconstruct them, which makes the proposed descriptor be significant discriminative, compact and robust. The experimental results show that the proposed descriptor can achieve better performance than similar methods.
|
|
Received: 30 October 2018
Published: 28 March 2019
|
|
|
|
Corresponding Authors:
Sheng-jun LIU
E-mail: 18246514@qq.com;shjliu.cg@csu.edu.cn
|
三维模型匹配的谱图小波描述符
为了实现三维模型的点-点匹配, 基于谱图小波变换（SGWT）构建点的描述符. 对三维模型各顶点处的脉冲函数进行多尺度谱图小波变换，因为这些小波系数能够充分反映模型各顶点处的多尺度几何信息，将它们依次作为元素形成多维向量. 该向量即为模型各点的谱图小波描述符，点描述符的欧式距离可以度量点与点之间的几何差异性. 由于谱图小波(SGW)同时使用低通和带通滤波器分析信号且能够稳定地重构信号, 这使得提出的描述符具有很好的形状分辨能力、紧凑性和鲁棒性. 实验结果显示，谱图小波描述符具有比同类方法更卓越的性能.
关键词：
拉普拉斯-贝尔特米算子,
模型匹配,
谱图小波（SGW）,
点描述符,
滤波器
|
|
| [1] |
BRONSTEIN A M, BRONSTEIN M M, OVSJANIKOV M. Feature-based methods in 3D shape analysis [M]//3D imaging, analysis and applications. London: Springer, 2012: 185–219.
|
|
|
| [2] |
SUN J, OVSJANIKOV M, GUIBAS L A concise and provably informative multi-scale signature based on heat diffusion[J]. Computer Graphics Forum, 2010, 28 (5): 1383- 1392
|
|
|
| [3] |
AUBRY M, SCHLICKEWEI U, CREMERS D. The wave kernel signature: a quantum mechanical approach to shape analysis [C] // IEEE International Conference on Computer Vision Workshops. Barcelona: IEEE, 2011: 1626–1633.
|
|
|
| [4] |
BOSCAINI D, MASCI J, MELZI S, et al Learning class: specific descriptors for deformable shapes using localized spectral convolutional networks[J]. Computer Graphics Forum, 2015, 34 (5): 13- 23
doi: 10.1111/cgf.2015.34.issue-5
|
|
|
| [5] |
SHUMAN D I, RICAUD B, VANDERGHEYNST P Vertex-frequency analysis on graphs[J]. Applied and Computational Harmonic Analysis, 2016, 40 (2): 260- 291
doi: 10.1016/j.acha.2015.02.005
|
|
|
| [6] |
MELZI S, OVSJANIKOV M, ROFFO G, et al Discrete time evolution process descriptor for shape analysis and matching[J]. ACM Transactions on Graphics (TOG), 2018, 37 (1): 4
|
|
|
| [7] |
LITMAN R, BRONSTEIN A M Learning spectral descriptors for deformable shape correspondence[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36 (1): 171
doi: 10.1109/TPAMI.2013.148
|
|
|
| [8] |
BOSCAINI D, MASCI J, RODOLà E, et al Anisotropic diffusion descriptors[J]. Computer Graphics Forum, 2016, 35 (2): 431- 441
doi: 10.1111/cgf.12844
|
|
|
| [9] |
HAMMOND D K, VANDERGHEYNST P, GRIBONVAL R Wavelets on graphs via spectral graph theory[J]. Applied and Computational Harmonic Analysis, 2011, 30 (2): 129- 150
doi: 10.1016/j.acha.2010.04.005
|
|
|
| [10] |
KIM W H, PACHAURI D, HATT C, et al. Wavelet based multi-scale shape features on arbitrary surfaces for cortical thickness discrimination [C] // Advances in Neural Information Processing Systems. Doha: Curran Associates Inc, 2012: 1241–1249.
|
|
|
| [11] |
KIM W H, CHUNG M K, SINGH V. Multi-resolution shape analysis via non-euclidean wavelets: applications to mesh segmentation and surface alignment problems [C] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Portland: IEEE, 2013: 2139–2146.
|
|
|
| [12] |
KIM W H, ADLURU N, CHUNG M K, et al. Multi-resolutional brain network filtering and analysis via wavelets on non-Euclidean space [C] // International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin: Springer, 2013: 643–651.
|
|
|
| [13] |
ZHONG M, QIN H Sparse approximation of 3D shapes via spectral graph wavelets[J]. The Visual Computer, 2014, 30 (6-8): 751- 761
doi: 10.1007/s00371-014-0971-0
|
|
|
| [14] |
TAN M, QIU A Spectral Laplace-Beltrami wavelets with applications in medical images[J]. IEEE Transactions on Medical Imaging, 2015, 34 (5): 1005- 1017
doi: 10.1109/TMI.2014.2363884
|
|
|
| [15] |
LI C, HAMZA A B A multiresolution descriptor for deformable 3D shape retrieval[J]. The Visual Computer, 2013, 29 (6-8): 513- 524
doi: 10.1007/s00371-013-0815-3
|
|
|
| [16] |
MEYER M, DESBRUN M, SCHR?DER P, et al. Discrete differential-geometry operators for triangulated 2-manifolds [M]//Visualization and mathematics III. Berlin: Springer, 2003: 35–57.
|
|
|
| [17] |
LéVY B, ZHANG H Spectral mesh processing[J]. Computer Graphics Forum, 2010, 29 (6): 1865- 1894
doi: 10.1111/j.1467-8659.2010.01655.x
|
|
|
| [18] |
BOGO F, ROMERO J, LOPER M, et al. FAUST: dataset and evaluation for 3d mesh registration [C] // IEEE Conference on Computer Vision and Pattern Recognition. Columbus: IEEE, 2014: 3794–3801.
|
|
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
