Hierarchical Superquadric Decomposition with Implicit Space Separation

TL;DR

This paper presents a hierarchical method for 3D object reconstruction using superquadrics, which recursively decomposes objects into finer details based on implicit space separation, demonstrating effective results on complex geometries.

Contribution

It introduces a novel hierarchical decomposition approach leveraging superquadric properties for 3D reconstruction, improving detail recovery over previous methods.

Findings

Effective reconstruction of diverse complex objects

Hierarchical decomposition improves detail accuracy

Method trained and validated on ShapeNet dataset

Abstract

We introduce a new method to reconstruct 3D objects using a set of volumetric primitives, i.e., superquadrics. The method hierarchically decomposes a target 3D object into pairs of superquadrics recovering finer and finer details. While such hierarchical methods have been studied before, we introduce a new way of splitting the object space using only properties of the predicted superquadrics. The method is trained and evaluated on the ShapeNet dataset. The results of our experiments suggest that reasonable reconstructions can be obtained with the proposed approach for a diverse set of objects with complex geometry.