›› 2012, Vol. 27 ›› Issue (6): 1092-1099.doi: 10.1007/s11390-012-1287-z

Special Issue: Computer Graphics and Multimedia

• Special Section on Computational Visual Media • Previous Articles     Next Articles

Multi-Scale Salient Features for Analyzing 3D Shapes

Yong-Liang Yang1,2 (杨永亮) and Chao-Hui Shen2 (沈超慧)   

  1. 1. King Abdullah University of Science and Technology, Thuwal, Saudi Arabia;
    2. Tsinghua National Lab for Informatics Science & Technology, Tsinghua University, Beijing 100084, China
  • Received:2012-09-05 Revised:2012-09-13 Online:2012-11-05 Published:2012-11-05
  • Supported by:

    This work was supported by the National Basic Research 973 Program of China under Grant No. 2011CB302203, the National Natural Science Foundation of China under Grant No. 61120106007, and the National High Technology Research and Development 863 Program of China under Grant No. 2012AA011801.

Extracting feature regions on mesh models is crucial for shape analysis and understanding. It can be widely used for various 3D content-based applications in graphics and geometry field. In this paper, we present a new algorithm of extracting multi-scale salient features on meshes. This is based on robust estimation of curvature on multiple scales. The coincidence between salient feature and the scale of interest can be established straightforwardly, where detailed feature appears on small scale and feature with more global shape information shows up on large scale. We demonstrate this kind of multi-scale description of features accords with human perception and can be further used for several applications as feature classification and viewpoint selection. Experiments exhibit that our method as a multi-scale analysis tool is very helpful for studying 3D shapes.

[1] Tangelder J W, Veltkamp R C. A survey of content based3D shape retrieval methods. In Proc. Shape Modeling andApplications 2004, June 2004, pp.145-156.

[2] Lee C H, Varshney A, Jacobs D W. Mesh saliency. ACMTrans. Graphics, 2005, 24(3): 659-666.

[3] Gal R, Cohen-Or D. Salient geometric features for partialshape matching and similarity. ACM Trans. Graphics, 2006,25(1): 130-150.

[4] Shilane P, Funkhouser T. Distinctive regions of 3D surfaces.ACM Trans. Graphics, 2007, 26(2): Article No. 7.

[5] Chen X, Saparov A, Pang B et al. Schelling points on 3Dsurface meshes. Trans. Graphics, 2012, 31(4), Article No. 29.

[6] Yang Y L, Shen C H. Multi-scale salient feature extraction onmesh models. In Proc. Computational Visual Media Confer-ence, Nov. 2012, pp.122-129.

[7] Gatzke T, Grimm C. Estimating curvature on triangularmeshes. Int. J. Shape Modeling, 2006, 12(1): 1-28.

[8] Yang Y L, Lai Y K, Hu S M et al. Robust principal curvatureson multiple scales. In Proc. the 4th SGP, 2006, pp.223-226.

[9] Pottmann H,Wallner J, Yang Y L, Lai Y K, Hu S M. Principalcurvatures from the integral invariant viewpoint. Computer Aided Geometric Design, 2007, 24(8-9): 428-442.

[10] Wang D, Li G, Jia W, Luo X. Saliency-driven scaling op-timization for image retargeting. Visual Computer, 2011,27(9): 853-860.

[11] Itti L, Koch C, Niebur E. A model of saliency-based visual at-tention for rapid scene analysis. IEEE Trans. Pattern Anal-ysis and Machine Intelligence, 1998, 20(11): 1254-1259.

[12] Miao Y, Feng J. Perceptual-saliency extremum lines for 3Ddshape illustration. Visual Computer, 2010, 26(6-8): 433-443.

[13] Witkin A P. Scale-space filtering. In Proc. the 8th Int. JointConf. Artifical Intelligence, Aug. 1983, Vol.2, pp.1019-1022.

[14] Lindeberg T. Feature detection with automatic scale selec-tion. Int. J. Computer Vision, 1998, 30(2): 79-116.

[15] Hoppe H. Progressive meshes. In Proc. the 23rd SIGGRAPH,Aug. 1996, pp.99-108.

[16] Zorin D, Schröder P, Sweldens W. Interactive multiresolutionmesh editing. In Proc. the 24th SIGGRAPH, Aug. 1997,pp.259-268.

[17] Hubeli A, Gross M. Multiresolution feature extraction for un-structured meshes. In Proc. Visualization 2001, Oct. 2001,pp.287-294.

[18] Clarenz U, Rumpf M, Telea A. Robust feature detection andlocal classification for surfaces based on moment analysis.IEEE Transactions on Visualization and Computer Graph-ics, 2004, 10(5): 516-524.

[19] Clarenz U, Griebel M, Rumpf M, Schweitzer M A, Telea A.Feature sensitive multiscale editing on surfaces. Visual Com-puter, 2004, 20(5): 329-343.

[20] Pauly M, Keiser R, Gross M. Multi-scale feature extractionon point-sampled surfaces. Computer Graphics Forum, 2003,22(3): 281-289.

[21] Gelfand N, Mitra N J, Guibas L J, Pottmann H. Robust globalregistration. In Proc. the 3rd SGP, July 2005, pp.197-206.

[22] Zou G, Hua J, Lai Z, Gu X, Dong M. Intrinsic geometric scalespace by shape diffusion. IEEE Transactions on Visualiza-tion and Computer Graphics, 2009, 15(6): 1193-1200.

[23] Sun J, Ovsjanikov M, Guibas L. A concise and provably infor-mative multi-scale signature based on heat diffusion. Com-puter Graphics Forum, 2009, 28(5): 1383-1392.

[24] Katz S, Tal A. Hierarchical mesh decomposition using fuzzyclustering and cuts. Trans. Graphics, 2003, 22(3): 954-961.

[25] Lai Y K, Zhou Q Y, Hu S M, Wallner J, Pottmann H. Ro-bust feature classification and editing. IEEE Transactions onVisualization and Computer Graphics, 2007, 13(1): 34-45.

[26] Johnson A. Spin-Images: A representation for 3-D surfacematching [Ph.D. Thesis]. Robotics Institute, Carnegie Mel-lon University, Pittsburgh, USA, August 1997.

[27] Cox T, Cox M. Multidimensional Scaling (2nd edition). Lon-don, UK: Chapman & Hall, 2001.

[28] Podolak J, Shilane P, Golovinskiy A, Rusinkiewicz S,Funkhouser T. A planar-reflective symmetry transform for 3Dshapes. ACM Trans. Graphics, 2006, 25(3): 549-559.

[29] Fu H, Cohen-Or D, Dror G et al. Upright orientation of man-made objects. Trans. Graphics, 2008, 27(3), Article No. 42.

[30] Lai Y K, Zhou Q Y, Hu S M, Wallner J, Pottmann H. Ro-bust feature classification and editing. IEEE Transactions onVisualization and Computer Graphics, 2007, 13(1): 34-45.

[31] Lai Y K, Hu S M, Fang T. Robust principal curvatures usingfeature adapted integral invariants. In Proc. SPM 2009, Oct.2009, pp.325-330.

[32] Yan D M, Wang W P, Liu Y, Yang Z. Variational mesh seg-mentation via quadric surface fitting. Computer-Aided De-sign, 2012, 44(11): 1072-1082.
No related articles found!
Full text



[1] Luo Yinfang;. Algorithm and Implementation of Parallel Multiplication in a Mixed Number System[J]. , 1988, 3(3): 203 -213 .
[2] Shen Li;. Testability Analysis at Switch Level for CMOS Circuits[J]. , 1990, 5(2): 197 -202 .
[3] Han Jianchao; Shi Zhongzhi;. Formalizing Default Reasoning[J]. , 1990, 5(4): 374 -378 .
[4] Huang Zhiyi; Hu Shouren;. Detection of And-Parallelism in Logic Programs[J]. , 1990, 5(4): 379 -387 .
[5] wang Xuejun; Shi Chunyi;. A Multiagent Dynamic interaction Testbed:Theoretic Framework, System Architecture and Experimentation[J]. , 1997, 12(2): 121 -132 .
[6] Chen Yangjun;. Counting and Topological Order[J]. , 1997, 12(6): 497 -509 .
[7] Qiang Wang, De-Bin Zhao, and Wen Gao. Context-Based 2D-VLC Entropy Coder in AVS Video Coding Standard[J]. , 2006, 21(3): 315 -322 .
[8] Sheng-You Lin and Jiao-Ying Shi. A Markov Random Field Model-Based Approach to Natural Image Matting[J]. , 2007, 22(1): 161 -167 .
[9] En-Jian Bai and Xiao-Juan Liu. Some Notes on Prime-Square Sequences[J]. , 2007, 22(3): 481 -486 .
[10] Rong-Hua Li and Chuan-Kun Wu. A Protocol for a Private Set-Operation[J]. , 2007, 22(6): 822 -829 .

ISSN 1000-9000(Print)

CN 11-2296/TP

Editorial Board
Author Guidelines
Journal of Computer Science and Technology
Institute of Computing Technology, Chinese Academy of Sciences
P.O. Box 2704, Beijing 100190 P.R. China
E-mail: jcst@ict.ac.cn
  Copyright ©2015 JCST, All Rights Reserved