MorphoSkel3D: Morphological Skeletonization of 3D Point Clouds for Informed Sampling in Object Classification and Retrieval

Pierre Onghena, Santiago Velasco-Forero, Beatriz Marcotegui

Mines Paris – PSL University Centre for Mathematical Morphology (CMM)

3DV 2025

Four point clouds in grey with their skeletal spheres colour-coded by radius: an earphone, a desk lamp, a piano and a human figure.

The skeletal spheres of MS3D together with its surface points, for examples of the ShapeNet and ModelNet datasets.

0 Training required
Lowest Chamfer distance
85.5% Classification at 64x sampling ratio

Abstract

Point clouds are a set of data points in space to represent the 3D geometry of objects. A fundamental step in the processing is to identify a subset of points to represent the shape. While traditional sampling methods often ignore to incorporate geometrical information, recent developments in learning-based sampling models have achieved significant levels of performance. With the integration of geometrical priors, the ability to learn and preserve the underlying structure can be enhanced when sampling. To shed light into the shape, a qualitative skeleton serves as an effective descriptor to guide sampling for both local and global geometries. In this paper, we introduce MorphoSkel3D as a new technique based on morphology to facilitate an efficient skeletonization of shapes. With its low computational cost, MorphoSkel3D is a unique, rule-based algorithm to benchmark its quality and performance on two large datasets, ModelNet and ShapeNet, under different sampling ratios. The results show that training with MorphoSkel3D leads to an informed and more accurate sampling in the practical application of object classification and point cloud retrieval.

Method Overview

Three-stage pipeline: surface reconstruction to a watertight mesh, the MorphoSkel3D dilation of the unsigned distance function, and the resulting skeleton used for informed sampling.
Overview of the shape-agnostic skeletonization pipeline. In the MorphoSkel3D module, the local maxima on the unsigned distance function of inner points reveal the set of maximal balls.

Citation

@inproceedings{onghena2025morphoskel3d,
  author    = {Onghena, Pierre and Velasco-Forero, Santiago and Marcotegui, Beatriz},
  booktitle = {2025 International Conference on 3D Vision (3DV)},
  title     = {{MorphoSkel3D}: Morphological Skeletonization of {3D} Point Clouds for Informed Sampling in Object Classification and Retrieval},
  year      = {2025},
  pages     = {1350--1359},
  publisher = {IEEE},
  doi       = {10.1109/3DV66043.2025.00128}
}