Print Email Facebook Twitter An end-to-end geometric deficiencies elimination algorithm for 3D meshes Title An end-to-end geometric deficiencies elimination algorithm for 3D meshes Author Ma, Bingtao (University of Chinese Academy of Sciences) Liu, Hongsen (University of Chinese Academy of Sciences) Nan, L. (TU Delft Urban Data Science) Tang, Xu (Chinese Academy of Sciences) Fan, Huijie (Chinese Academy of Sciences) Cong, Yang (Chinese Academy of Sciences) Date 2021 Abstract The 3D mesh is an important representation of geometric data. It is widely used in computer graphics and has attracted more attention in computer vision community recently. However, in the generation of mesh data, geometric deficiencies (e.g., duplicate elements, degenerate faces, isolated vertices, self-intersection, and inner faces) are unavoidable. Geometric deficiencies may violate the topology structure of an object and affect the use of 3D meshes. In this paper, we propose an end-to-end algorithm to eliminate geometric deficiencies effectively and efficiently for 3D meshes in a specific and reasonable order. Specifically, duplicate elements can be first eliminated by assessing appear times of vertices or faces. Then, degenerate faces can be removed according to the outer product of two edges. Next, since isolated vertices do not appear in any face vertices, they can be deleted directly. Afterward, self-intersecting faces are detected and remeshed by using an AABB tree. Finally, we detect and remove an inner face according to whether multiple random rays shooted from a face can reach infinity. Experiments on ModelNet40 dataset illustrate that our method can eliminate the deficiencies of 3D meshes thoroughly. Subject 3D MeshGeometric deficienciesMesh repair To reference this document use: http://resolver.tudelft.nl/uuid:f5ffc3f8-bdc6-4f97-89fc-29298b60dbd7 DOI https://doi.org/10.1109/YAC51587.2020.9337658 Publisher IEEE Embargo date 2021-08-05 ISBN 978-1-7281-7684-0 Source Proceedings of the 35th Youth Academic Annual Conference of Chinese Association of Automation Bibliographical note Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type conference paper Rights © 2021 Bingtao Ma, Hongsen Liu, L. Nan, Xu Tang, Huijie Fan, Yang Cong Files PDF 09337658.pdf 667.05 KB Close viewer /islandora/object/uuid:f5ffc3f8-bdc6-4f97-89fc-29298b60dbd7/datastream/OBJ/view