Shape Segmentation by Approximate Convexity Analysis

We present a shape segmentation method for complete and incomplete shapes. The key idea is to directly optimize the decomposition based on a characterization of the expected geometry of a part in a shape. Rather than setting the number of parts in advance, we search for the smallest number of parts that admit the geometric characterization of the parts. The segmentation is based on an intermediate-level analysis, where first the shape is decomposed into approximate convex components, which are then merged into consistent parts based on a nonlocal geometric signature. Our method is designed to handle incomplete shapes, represented by point clouds. We show segmentation results on shapes acquired by a range scanner, and an analysis of the robustness of our method to missing regions. Moreover, our method yields results that are comparable to state-of-the-art techniques evaluated on complete shapes.

[1]  John Hart,et al.  ACM Transactions on Graphics , 2004, SIGGRAPH 2004.

[2]  Junsong Yuan,et al.  Minimum near-convex decomposition for robust shape representation , 2011, 2011 International Conference on Computer Vision.

[3]  Thorsten Joachims,et al.  Semantic Labeling of 3D Point Clouds for Indoor Scenes , 2011, NIPS.

[4]  Daniel Cohen-Or,et al.  Weak Convex Decomposition by Lines‐of‐sight , 2013, SGP '13.

[5]  Lin Lu,et al.  Variational 3D Shape Segmentation for Bounding Volume Computation , 2007, Comput. Graph. Forum.

[6]  Alla Sheffer,et al.  Model Composition from Interchangeable Components , 2007 .

[7]  Martial Hebert,et al.  3-D scene analysis via sequenced predictions over points and regions , 2011, 2011 IEEE International Conference on Robotics and Automation.

[8]  Daniel Cohen-Or,et al.  Unsupervised co-segmentation of a set of shapes via descriptor-space spectral clustering , 2011, ACM Trans. Graph..

[9]  Daniel Cohen-Or,et al.  Surface reconstruction using local shape priors , 2007, Symposium on Geometry Processing.

[10]  Marco Attene,et al.  Hierarchical Structure Recovery of Point‐Sampled Surfaces , 2010, Comput. Graph. Forum.

[11]  Aaron Hertzmann,et al.  Learning 3D mesh segmentation and labeling , 2010, SIGGRAPH 2010.

[12]  Cohen-OrDaniel,et al.  Consistent mesh partitioning and skeletonisation using the shape diameter function , 2008 .

[13]  Thomas A. Funkhouser,et al.  A benchmark for 3D mesh segmentation , 2009, ACM Trans. Graph..

[14]  Nancy M. Amato,et al.  Approximate convex decomposition of polyhedra , 2004, Symposium on Solid and Physical Modeling.

[15]  Jianfei Cai,et al.  Variational mesh decomposition , 2012, TOGS.

[16]  Ligang Liu,et al.  Co‐Segmentation of 3D Shapes via Subspace Clustering , 2012, Comput. Graph. Forum.

[17]  T. Funkhouser,et al.  Randomized cuts for 3D mesh analysis , 2008, SIGGRAPH 2008.

[18]  Vladlen Koltun,et al.  Joint shape segmentation with linear programming , 2011, ACM Trans. Graph..

[19]  Kun Zhou,et al.  An interactive approach to semantic modeling of indoor scenes with an RGBD camera , 2012, ACM Trans. Graph..

[20]  Nancy M. Amato,et al.  Approximate convex decomposition of polyhedra , 2007, Symposium on Solid and Physical Modeling.

[21]  Min Meng,et al.  Unsupervised co-segmentation for 3D shapes using iterative multi-label optimization , 2013, Comput. Aided Des..

[22]  Daniel Cohen-Or,et al.  A Part‐aware Surface Metric for Shape Analysis , 2009, Comput. Graph. Forum.

[23]  Florent Lafarge,et al.  Surface Reconstruction through Point Set Structuring , 2013, Comput. Graph. Forum.

[24]  Daniel Cohen-Or,et al.  GlobFit: consistently fitting primitives by discovering global relations , 2011, ACM Trans. Graph..

[25]  Pengfei Xu,et al.  Mesh Segmentation with Concavity-Aware Fields , 2012, IEEE Transactions on Visualization and Computer Graphics.

[26]  Reinhard Klein,et al.  Completion and Reconstruction with Primitive Shapes , 2009, Comput. Graph. Forum.

[27]  Leonidas J. Guibas,et al.  Acquiring 3D indoor environments with variability and repetition , 2012, ACM Trans. Graph..

[28]  Thomas A. Funkhouser,et al.  Min-cut based segmentation of point clouds , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[29]  Thomas Funkhouser,et al.  A benchmark for 3D mesh segmentation , 2009, SIGGRAPH 2009.

[30]  Toby Sharp,et al.  Real-time human pose recognition in parts from single depth images , 2011, CVPR.

[31]  Derek Nowrouzezahrai,et al.  Multi‐objective shape segmentation and labeling , 2009, Comput. Graph. Forum.

[32]  Aaron Hertzmann,et al.  Learning 3D mesh segmentation and labeling , 2010, ACM Trans. Graph..

[33]  Thomas A. Funkhouser,et al.  Randomized cuts for 3D mesh analysis , 2008, SIGGRAPH Asia '08.

[34]  Daniel Cohen-Or,et al.  Consistent mesh partitioning and skeletonisation using the shape diameter function , 2008, The Visual Computer.

[35]  Ariel Shamir,et al.  A survey on Mesh Segmentation Techniques , 2008, Comput. Graph. Forum.

[36]  Tamy Boubekeur,et al.  Sphere-Meshes , 2013, ACM Trans. Graph..

[37]  Ke Xie,et al.  A search-classify approach for cluttered indoor scene understanding , 2012, ACM Trans. Graph..

[38]  Marco Attene,et al.  Hierarchical Convex Approximation of 3D Shapes for Fast Region Selection , 2008, Comput. Graph. Forum.

[39]  Alla Sheffer,et al.  Model Composition from Interchangeable Components , 2007, 15th Pacific Conference on Computer Graphics and Applications (PG'07).

[40]  Donald D. Hoffman,et al.  Parts of recognition , 1984, Cognition.

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

[42]  Ben Taskar,et al.  Discriminative learning of Markov random fields for segmentation of 3D scan data , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[43]  N. Mitra,et al.  GlobFit: consistently fitting primitives by discovering global relations , 2011, SIGGRAPH 2011.