凹性誘導距離による非配向点群の分解
Concavity-Induced Distance for Unoriented Point Cloud Decomposition
点群中の2点間の非類似度を測る凹性誘導距離(CID)を提案し、メッシュ化や法線推定なしに点群のインスタンス分割や凸部分へのグループ化を可能にした。
著者: Ruoyu Wang, Yanfei Xue, Bharath Surianarayanan, Dong Tian, Chen Feng
分類: cs.CV, cs.RO
原文アブストラクト
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: https://ai4ce.github.io/CID/
