Hierarchical Superquadric Decomposition with Implicit Space Separation

2022/09/15 by Jaka Sircelj, Peter Peer, Šircelj, Jaka +5
Computer Science · Engineering · #3D Shape Modeling and Analysis #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Retrieval and Classification Techniques

paper · pdf · doi:10.48550/arxiv.2209.07619

openalex publication_date 2022/09/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Related

• SuperDec: 3D Scene Decomposition with Superquadric Primitives
• Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids
• Segmentation and Recovery of Superquadric Models using Convolutional Neural Networks
• Iterative Superquadric Recomposition of 3D Objects from Multiple Views
• Self-supervised Learning of Hybrid Part-aware 3D Representation of 2D Gaussians and Superquadrics