Primitive-based Shape Abstraction via Nonparametric Bayesian Inference

TL;DR

This paper introduces a non-parametric Bayesian method for 3D shape abstraction that infers an optimal set of geometric primitives from point clouds, outperforming existing techniques in accuracy and generality.

Contribution

The paper presents a novel Bayesian approach using Gaussian Superquadric Taper Models and the Chinese Restaurant Process for shape abstraction, enabling automatic inference of primitive number and improved accuracy.

Findings

Outperforms state-of-the-art in accuracy

Generalizes well to various object types

Automatically infers the number of primitives

Abstract

3D shape abstraction has drawn great interest over the years. Apart from low-level representations such as meshes and voxels, researchers also seek to semantically abstract complex objects with basic geometric primitives. Recent deep learning methods rely heavily on datasets, with limited generality to unseen categories. Furthermore, abstracting an object accurately yet with a small number of primitives still remains a challenge. In this paper, we propose a novel non-parametric Bayesian statistical method to infer an abstraction, consisting of an unknown number of geometric primitives, from a point cloud. We model the generation of points as observations sampled from an infinite mixture of Gaussian Superquadric Taper Models (GSTM). Our approach formulates the abstraction as a clustering problem, in which: 1) each point is assigned to a cluster via the Chinese Restaurant Process (CRP); 2) a primitive representation is optimized for each cluster, and 3) a merging post-process is incorporated to provide a concise representation. We conduct extensive experiments on two datasets. The results indicate that our method outperforms the state-of-the-art in terms of accuracy and is generalizable to various types of objects.