Primitive-based Shape Abstraction via Nonparametric Bayesian Inference
This addresses the challenge of creating concise and accurate shape abstractions for 3D modeling and computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of abstracting 3D shapes into geometric primitives by proposing a non-parametric Bayesian method that infers an unknown number of primitives from point clouds, achieving state-of-the-art accuracy and generalizability across object types.
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.