Part‐type Segmentation of Articulated Voxel‐Shapes using the Junction Rule

We present a part‐type segmentation method for articulated voxel‐shapes based on curve skeletons. Shapes are considered to consist of several simpler, intersecting shapes. Our method is based on the junction rule: the observation that two intersecting shapes generate an additional junction in their joined curve‐skeleton near the place of intersection. For each curve‐skeleton point, we construct a piecewise‐geodesic loop on the shape surface. Starting from the junctions, we search along the curve skeleton for points whose associated loops make for suitable part cuts. The segmentations are robust to noise and discretization artifacts, because the curve skeletonization incorporates a single user‐parameter to filter spurious curve‐skeleton branches. Furthermore, segment borders are smooth and minimally twisting by construction. We demonstrate our method on several real‐world examples and compare it to existing part‐type segmentation methods.

[1]  Ayellet Tal,et al.  Hierarchical mesh decomposition using fuzzy clustering and cuts , 2003, ACM Trans. Graph..

[2]  Ariel Shamir A formulation of boundary mesh segmentation , 2004, Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004..

[3]  Gábor Székely,et al.  Multiscale Medial Loci and Their Properties , 2003, International Journal of Computer Vision.

[4]  Balasubramanian Raman,et al.  Computing hierarchical curve-skeletons of 3D objects , 2005, The Visual Computer.

[5]  Alexandru Telea,et al.  Skeleton-based Hierarchical Shape Segmentation , 2007, IEEE International Conference on Shape Modeling and Applications 2007 (SMI '07).

[6]  Taku Komura,et al.  Topology matching for fully automatic similarity estimation of 3D shapes , 2001, SIGGRAPH.

[7]  Marco Attene,et al.  Mesh Segmentation - A Comparative Study , 2006, IEEE International Conference on Shape Modeling and Applications 2006 (SMI'06).

[8]  Donald D. Hoffman,et al.  Salience of visual parts , 1997, Cognition.

[9]  Hans-Peter Seidel,et al.  Mesh scissoring with minima rule and part salience , 2005, Comput. Aided Geom. Des..

[10]  Jovan Popovic,et al.  Deformation transfer for triangle meshes , 2004, ACM Trans. Graph..

[11]  Tiow Seng Tan,et al.  Decomposing polygon meshes for interactive applications , 2001, I3D '01.

[12]  Mohamed Daoudi,et al.  Topology driven 3D mesh hierarchical segmentation , 2007, IEEE International Conference on Shape Modeling and Applications 2007 (SMI '07).

[13]  Ayellet Tal,et al.  Mesh segmentation using feature point and core extraction , 2005, The Visual Computer.

[14]  Tamal K. Dey,et al.  Defining and computing curve-skeletons with medial geodesic function , 2006, SGP '06.

[15]  Marco Attene,et al.  Hierarchical mesh segmentation based on fitting primitives , 2006, The Visual Computer.

[16]  Jarek Rossignac,et al.  Plumber: A Multi-scale Decomposition of 3D Shapes into Tubular Primitives and Bodies , 2004 .

[17]  Nancy M. Amato,et al.  Simultaneous shape decomposition and skeletonization , 2006, SPM '06.

[18]  Alexandru Telea,et al.  Computing Multiscale Curve and Surface Skeletons of Genus 0 Shapes Using a Global Importance Measure , 2008, IEEE Transactions on Visualization and Computer Graphics.

[19]  Jovan Popović,et al.  Deformation transfer for triangle meshes , 2004, SIGGRAPH 2004.

[20]  J. Rossignac,et al.  Plumber: a method for a multi-scale decomposition of 3D shapes into tubular primitives and bodies , 2004, SM '04.