cs.LGNov 1, 2026

Autoencoder Based Deep Clustering of Point Clouds

Authors: Nader Alfares, Guangmingmei Yang, David J. Miller, George Kesidis

Organizations: School of EECS, Penn State, University Park, PA, USA

Abstract

Motivated by a problem in Generative Specification-Producing AIs (SPAIs), we focus on a problem of deep clustering of three-dimensional shapes specified by point clouds. After reviewing clustering and deep clustering, we study the fully unsupervised pipeline in which a FoldingNet autoencoder is first trained for reconstruction and then K-means++ is then applied to the resulting codewords. We report clustering accuracy (ACC), normalized mutual information (NMI) and adjusted Rand index (ARI) on ModelNet10 and ModelNet40 datasets, as a function of the number of clusters K. We also provide t-SNE visualizations of the codewords, and discuss the choice of K.

Figures & tables

Explore similar work

CardsList
  1. point2vec for Self-Supervised Representation Learning on Point Clouds

    Mar 29, 2023Karim Knaebel, Jonas Schult, Alexander Hermans +1Self-Supervised Point Cloud LearningPoint Cloud Learning

  2. Learning to Tessellate: Point Cloud Generation via Recursive Spectral Partitioning

    Aug 3, 2026Monan Sun, Bangzhen Liu, Huaidong Zhang +1Point Cloud Learning3D Shape Generation