Deep Learning for Unsupervised 3D Shape Representation with Superquadrics
Open Access
Abstract
The representation of 3D shapes from point clouds remains a fundamental challenge in computer vision. A common approach decomposes 3D objects into interpretable geometric primitives, enabling compact, structured, and efficient representations. Building upon prior frameworks, this study introduces an enhanced unsupervised deep learning approach for 3D shape representation using superquadrics. The proposed framework fits a set of superquadric primitives to 3D objects through a fully integrated, differentiable pipeline that enables efficient optimization and parameter learning, directly extracting geometric structure from 3D point clouds without requiring ground-truth segmentation labels. This work introduces three key advancements that substantially improve representation quality, interpretability, and evaluation rigor: (1) A uniform sampling strategy that enhances training stability compared with random sampling used in earlier models; (2) An overlapping loss that penalizes intersections between primitives, reducing redundancy and improving reconstruction coherence; and (3) A novel evaluation framework comprising Primitive Accuracy, Structural Accuracy, and Overlapping Percentage metrics. This new metric design transitions from point-based to structure-aware assessment, enabling fairer and more interpretable comparison across primitive-based models. Comprehensive evaluations on benchmark 3D shape datasets demonstrate that the proposed modifications yield coherent, compact, and semantically consistent shape representations, establishing a robust foundation for interpretable and quantitative evaluation in primitive-based 3D reconstruction.Keywords
All Related Versions
Funding Information
- Deutsches Zentrum für Luft- und Raumfahrt (50WK2270F)
- Brandenburg University of Technology Cottbus–Senftenberg
This publication has 35 references indexed in Scilit:
- SfmCAD: Unsupervised CAD Reconstruction by Learning Sketch-based Feature Modeling Operations2024
- Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly2023
- Unsupervised Description of 3D Shapes by Superquadrics Using Deep Learning2023
- DGCNN: Disordered graph convolutional neural network based on the Gaussian mixture modelNeurocomputing, 2018
- Superquadrics for segmenting and modeling range dataIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997
- A method for registration of 3-D shapesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992
- Recovery of parametric models from range images: the case for superquadrics with global deformationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990
- Constraints on deformable models:Recovering 3D shape and nonrigid motionArtificial Intelligence, 1988
- Perceptual organization and the representation of natural formArtificial Intelligence, 1986
- Superquadrics and Angle-Preserving TransformationsIEEE Computer Graphics and Applications, 1981