跳到主要导航 跳到搜索 跳到主要内容

TopoSeg: Topology-aware Segmentation for Point Clouds

  • Weiquan Liu
  • , Hanyun Guo
  • , Weini Zhang
  • , Yu Zang*
  • , Cheng Wang
  • , Jonathan Li
  • *此作品的通讯作者
  • Xiamen University
  • University of Waterloo

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

Point cloud segmentation plays an important role in AI applications such as autonomous driving, AR, and VR. However, previous point cloud segmentation neural networks rarely pay attention to the topological correctness of the segmentation results. In this paper, focusing on the perspective of topology awareness. First, to optimize the distribution of segmented predictions from the perspective of topology, we introduce the persistent homology theory in topology into a 3D point cloud deep learning framework. Second, we propose a topology-aware 3D point cloud segmentation module, TopoSeg. Specifically, we design a topological loss function embedded in TopoSeg module, which imposes topological constraints on the segmentation of 3D point clouds. Experiments show that our proposed TopoSeg module can be easily embedded into the point cloud segmentation network and improve the segmentation performance. In addition, based on the constructed topology loss function, we propose a topology-aware point cloud edge extraction algorithm, which is demonstrated that has strong robustness.

源语言英语
主期刊名Proceedings of the 31st International Joint Conference on Artificial Intelligence, IJCAI 2022
编辑Luc De Raedt, Luc De Raedt
出版商International Joint Conferences on Artificial Intelligence
页1201-1208
页数8
ISBN(电子版)9781956792003
DOI
出版状态已出版 - 2022
已对外发布是
活动31st International Joint Conference on Artificial Intelligence, IJCAI 2022 - Vienna, 奥地利
期限: 23 7月 2022 → 29 7月 2022

丛书

姓名IJCAI International Joint Conference on Artificial Intelligence
ISSN(印刷版)1045-0823

会议

会议31st International Joint Conference on Artificial Intelligence, IJCAI 2022
国家/地区奥地利
市Vienna
时期23/07/22 → 29/07/22

学术指纹

探究 'TopoSeg: Topology-aware Segmentation for Point Clouds' 的科研主题。它们共同构成独一无二的学术指纹。

引用此