CPCS: Critical Points Guided Clustering and Sampling for Point Cloud Analysis

Wei Wang, Zhiwen Shao, Wencai Zhong, Lizhuang Ma*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

3D vision based on irregular point sequences has gained increasing attention, with current methods depending on random or farthest point sampling. However, the existing sampling methods either measure the distance in the Euclidean space and ignore the high-level properties, or just sample from point clouds only with the largest distance. To tackle these limitations, we introduce the Expectation-Maxi mization Attention module, to find the critical subset points and cluster the other points around them. Moreover, we explore a point cloud sampling strategy to sample points based on the critical subset. Extensive experiments demonstrate the effectiveness of our method for several popular point cloud analysis tasks. Our module achieves the accuracy of 93.3% on ModelNet40 with only 1024 points for classification task.

Original languageEnglish
Title of host publicationNeural Information Processing - 27th International Conference, ICONIP 2020, Proceedings
EditorsHaiqin Yang, Kitsuchart Pasupa, Andrew Chi-Sing Leung, James T. Kwok, Jonathan H. Chan, Irwin King
PublisherSpringer Science and Business Media Deutschland GmbH
Pages327-335
Number of pages9
ISBN (Print)9783030638191
DOIs
StatePublished - 2020
Event27th International Conference on Neural Information Processing, ICONIP 2020 - Bangkok, Thailand
Duration: 18 Nov 202022 Nov 2020

Publication series

NameCommunications in Computer and Information Science
Volume1332
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference27th International Conference on Neural Information Processing, ICONIP 2020
Country/TerritoryThailand
CityBangkok
Period18/11/2022/11/20

Keywords

  • Attention mechanism
  • Expectation maximization
  • Point cloud
  • Sampling

Fingerprint

Dive into the research topics of 'CPCS: Critical Points Guided Clustering and Sampling for Point Cloud Analysis'. Together they form a unique fingerprint.

Cite this