Concavity-Induced Distance for Unoriented Point Cloud Decomposition

Ruoyu Wang, Yanfei Xue, Bharath Surianarayanan, Dong Tian, Chen Feng

Research output: Contribution to journalArticlepeer-review


We propose Concavity-induced Distance (CID) as a novel way to measure the dissimilarity between a pair of points in an unoriented point cloud. CID indicates the likelihood of two points or two sets of points belonging to different convex parts of an underlying shape represented as a point cloud. After analyzing its properties, we demonstrate how CID can benefit point cloud analysis without the need for meshing or normal estimation, which is beneficial for robotics applications when dealing with raw point cloud observations. By randomly selecting very few points for manual labeling, a CID-based point cloud instance segmentation via label propagation achieves comparable average precision as recent supervised deep learning approaches, on S3DIS and ScanNet datasets. Moreover, CID can be used to group points into approximately convex parts whose convex hulls can be used as compact scene representations in robotics, and it outperforms the baseline method in terms of grouping quality. Our project website is available at:

Original languageEnglish (US)
Pages (from-to)4807-4814
Number of pages8
JournalIEEE Robotics and Automation Letters
Issue number8
StatePublished - Aug 1 2023


  • Object detection
  • computational geometry
  • segmentation and categorization

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Biomedical Engineering
  • Human-Computer Interaction
  • Mechanical Engineering
  • Computer Vision and Pattern Recognition
  • Computer Science Applications
  • Control and Optimization
  • Artificial Intelligence


Dive into the research topics of 'Concavity-Induced Distance for Unoriented Point Cloud Decomposition'. Together they form a unique fingerprint.

Cite this