SuperFlex: Deformable Superquadrics for Point Cloud Decomposition

• URL: http://arxiv.org/abs/2607.01015v1
• Date: Wed, 01 Jul 2026 14:51:14 GMT
• Title: SuperFlex: Deformable Superquadrics for Point Cloud Decomposition
• Abstract summary: Superquadrics have proven to provide a compact, geometrically meaningful representation for 3D objects.<n>Existing methods suffer from limited reconstruction accuracy, are restricted to rigid primitives, and lack robustness to partial point clouds.<n>We present SuperFlex, an enhanced framework that expands the expressive power and applicability of superquadric decompositions.
• Score: 49.51169535433531
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes [20.601722393809244]
  We introduce MetroGS, a novel framework for efficient and robust reconstruction in complex urban environments.<n>Our method is built upon a distributed 2D Gaussian Splatting representation as the core foundation.<n>Experiments on large-scale urban datasets demonstrate that MetroGS achieves superior geometric accuracy, rendering quality.
  arXiv  Detail & Related papers  (2025-11-24T14:34:19Z)
• Simba: Towards High-Fidelity and Geometrically-Consistent Point Cloud Completion via Transformation Diffusion [31.34032485865941]
  We introduce Simba, a novel framework that reformulates point-wise transformation regression as a distribution learning problem.<n>Our approach integrates symmetry priors with the powerful generative capabilities of diffusion models, avoiding instance-specific memorization.
  arXiv  Detail & Related papers  (2025-11-20T09:02:42Z)
• Rethinking Multimodal Point Cloud Completion: A Completion-by-Correction Perspective [8.276620253870338]
  Point cloud completion aims to reconstruct complete 3D shapes from partial observations.<n>Most methods still follow a Completion-by-Inpainting paradigm.<n>We propose Completion-by-Correction, which begins with a complete shape prior and performs feature-space correction to align it with the partial observation.
  arXiv  Detail & Related papers  (2025-11-15T11:51:13Z)
• Faithful Contouring: Near-Lossless 3D Voxel Representation Free from Iso-surface [49.742538510885]
  We propose Faithful Contouring, a voxelized representation that achieves near-lossless fidelity in 3D meshes.<n>The proposed method also shows flexibility and improvement for existing representation.
  arXiv  Detail & Related papers  (2025-11-06T03:56:12Z)
• Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes [60.92139345612904]
  We present Light-SQ, a novel superquadric-based optimization framework.<n>We propose a block-regrow-fill strategy guided by structure-aware volumetric decomposition.<n>Experiments demonstrate that Light-SQ enables efficient, high-fidelity, and editable shape abstraction with superquadrics.
  arXiv  Detail & Related papers  (2025-09-29T16:18:32Z)
• On the Geometric Accuracy of Implicit and Primitive-based Representations Derived from View Rendering Constraints [15.120134539151236]
  We compare implicit and explicit Novel View Synthesis methods for space-based 3D object reconstruction.<n>We show embeddings do not translate into meaningful gains in geometric accuracy.<n>Our findings clarify the limits of appearance embeddings for geometry-centric tasks.
  arXiv  Detail & Related papers  (2025-09-12T13:37:18Z)
• Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis [51.37795317716487]
  We propose the Adaptive Point-Prompt Tuning (APPT) method, which fine-tunes pre-trained models with a modest number of parameters.<n>We convert raw point clouds into point embeddings by aggregating local geometry to capture spatial features followed by linear layers.<n>To calibrate self-attention across source domains of any modality to 3D, we introduce a prompt generator that shares weights with the point embedding module.
  arXiv  Detail & Related papers  (2025-08-30T06:02:21Z)
• SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling [79.56581753856452]
  SparseFlex is a novel sparse-structured isosurface representation that enables differentiable mesh reconstruction at resolutions up to $10243$ directly from rendering losses.<n>By enabling high-resolution, differentiable mesh reconstruction and generation with rendering losses, SparseFlex significantly advances the state-of-the-art in 3D shape representation and modeling.
  arXiv  Detail & Related papers  (2025-03-27T17:46:42Z)
• HORT: Monocular Hand-held Objects Reconstruction with Transformers [61.36376511119355]
  Reconstructing hand-held objects in 3D from monocular images is a significant challenge in computer vision.<n>We propose a transformer-based model to efficiently reconstruct dense 3D point clouds of hand-held objects.<n>Our method achieves state-of-the-art accuracy with much faster inference speed, while generalizing well to in-the-wild images.
  arXiv  Detail & Related papers  (2025-03-27T09:45:09Z)
• Hyperbolic-constraint Point Cloud Reconstruction from Single RGB-D Images [19.23499128175523]
  We introduce hyperbolic space to 3D point cloud reconstruction, enabling the model to represent and understand complex hierarchical structures in point clouds with low distortion.<n>Our model outperforms most existing models, and ablation studies demonstrate the significance of our model and its components.
  arXiv  Detail & Related papers  (2024-12-12T08:27:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.