4.7 Article

SEG-MAT: 3D Shape Segmentation Using Medial Axis Transform

期刊

出版社

IEEE COMPUTER SOC
DOI: 10.1109/TVCG.2020.3032566

关键词

Shape analysis; shape segmentation; medial axis transform; geometry

资金

  1. Gottfried Wilhelm Leibniz program by DFG
  2. National Natural Science Foundation of China (NSFC) [61772301, 61772016]

向作者/读者索取更多资源

Segmenting arbitrary 3D objects into meaningful constituent parts is a crucial problem in computer graphics applications. Existing methods for 3D shape segmentation are limited by their reliance on low-level features and lack of global consideration, resulting in complex geometry processing and slow computation. This paper proposes SEG-MAT, a novel and efficient method based on the medial axis transform, which encodes rich geometric and structural information and effectively identifies various types of junctions between different parts of a 3D shape. Extensive evaluations demonstrate that our method outperforms state-of-the-art techniques in terms of segmentation quality and speed.
Segmenting arbitrary 3D objects into constituent parts that are structurally meaningful is a fundamental problem encountered in a wide range of computer graphics applications. Existing methods for 3D shape segmentation suffer from complex geometry processing and heavy computation caused by using low-level features and fragmented segmentation results due to the lack of global consideration. We present an efficient method, called SEG-MAT, based on the medial axis transform (MAT) of the input shape. Specifically, with the rich geometrical and structural information encoded in the MAT, we are able to develop a simple and principled approach to effectively identify the various types of junctions between different parts of a 3D shape. Extensive evaluations and comparisons show that our method outperforms the state-of-the-art methods in terms of segmentation quality and is also one order of magnitude faster.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据