SuperFlex: Deformable Superquadrics for Point Cloud Decomposition
For 3D computer vision and graphics, this provides a more accurate and flexible primitive-based representation for point cloud decomposition, though it is an incremental enhancement of existing superquadric methods.
SuperFlex improves superquadric-based 3D point cloud decomposition by introducing a novel loss for better reconstruction accuracy, adding bending and tapering deformations for curved/asymmetric shapes, and training a model robust to partial real-world data, achieving substantial accuracy gains over baselines.
Superquadrics have proven to provide a compact, geometrically meaningful representation for 3D objects. However, existing methods suffer from limited reconstruction accuracy, are restricted to rigid primitives, and lack robustness to partial point clouds. In this work, we present SuperFlex, an enhanced framework that expands the expressive power and applicability of superquadric decompositions. First, we introduce a novel loss formulation which significantly improves reconstruction accuracy. Second, we include bending and tapering deformations, enabling high-fidelity representation of curved and asymmetric geometries. Finally, we leverage these high-quality decompositions as supervision to train a model that is robust to partial real-world point clouds. Experiments demonstrate substantial improvements in reconstruction accuracy over both optimization- and learning-based baselines while maintaining a highly compact primitive representation.