An End-to-End Geometric Deficiency Elimination Algorithm for 3D Meshes

The 3D mesh is an important representation of geometric data. In the generation of mesh data, geometric deficiencies (e.g., duplicate elements, degenerate faces, isolated vertices, self-intersection, and inner faces) are unavoidable and may violate the topology structure of an object. In this paper, we propose an effective and efficient geometric deficiency elimination algorithm for 3D meshes. Specifically, duplicate elements can be eliminated by assessing the occurrence times of vertices or faces; degenerate faces can be removed according to the outer product of two edges; since isolated vertices do not appear in any face vertices, they can be deleted directly; self-intersecting faces are detected using an AABB tree and remeshed afterward; by simulating whether multiple random rays that shoot from a face can reach infinity, we can judge whether the surface is an inner face, then decide to delete it or not. Experiments on ModelNet40 dataset illustrate that our method can eliminate the deficiencies of the 3D mesh thoroughly.

[1]  Jianxiong Xiao,et al.  3D ShapeNets: A deep representation for volumetric shapes , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Konrad Polthier,et al.  Robust and High Fidelity Mesh Denoising , 2017, IEEE Transactions on Visualization and Computer Graphics.

[3]  Yang Cong,et al.  L3DOC: Lifelong 3D Object Classification , 2019, 1912.06135.

[4]  Haibin Yu,et al.  Speedup 3-D Texture-Less Object Recognition Against Self-Occlusion for Intelligent Manufacturing , 2019, IEEE Transactions on Cybernetics.

[5]  Xin Tong,et al.  Mesh denoising via cascaded normal regression , 2016, ACM Trans. Graph..

[6]  Wei Liu,et al.  Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images , 2018, ECCV.

[7]  Matteo Matteucci,et al.  Real-Time CPU-Based Large-Scale Three-Dimensional Mesh Reconstruction , 2018, IEEE Robotics and Automation Letters.

[8]  Torsten Sattler,et al.  Incremental Visual-Inertial 3D Mesh Generation with Structural Regularities , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[9]  Greg Turk,et al.  Interior/exterior classification of polygonal models , 2000, Proceedings Visualization 2000. VIS 2000 (Cat. No.00CH37145).

[10]  James M. Rehg,et al.  3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[11]  Kenshi Takayama,et al.  A Simple Method for Correcting Facet Orientations in Polygon Meshes Based on Ray Casting , 2014 .

[12]  Olga Sorkine-Hornung,et al.  Robust inside-outside segmentation using generalized winding numbers , 2013, ACM Trans. Graph..

[13]  G. Caumon,et al.  Surface-Based 3D Modeling of Geological Structures , 2009 .

[14]  Leonidas J. Guibas,et al.  ShapeNet: An Information-Rich 3D Model Repository , 2015, ArXiv.

[15]  Hongyi Xu,et al.  Signed distance fields for polygon soup meshes , 2014, Graphics Interface.

[16]  Yandong Tang,et al.  Robust 3-D Object Recognition via View-Specific Constraint , 2021, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[17]  Edward K. Wong,et al.  DeepShape: Deep-Learned Shape Descriptor for 3D Shape Retrieval , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Daniel Cremers,et al.  The wave kernel signature: A quantum mechanical approach to shape analysis , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[19]  Dongdong Hou,et al.  Semantic-Transferable Weakly-Supervised Endoscopic Lesions Segmentation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[20]  Michael Garland,et al.  Surface simplification using quadric error metrics , 1997, SIGGRAPH.