# Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes

arXiv: https://arxiv.org/abs/2509.24986 · HTML: https://mlsanity.com/paper/2509.24986/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Builds on (most cited first, 22 of 22)

- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets](https://mlsanity.com/paper/2406.13897/) (2024)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [Learning Shape Abstractions by Assembling Volumetric Primitives](https://mlsanity.com/paper/1612.00404/) (2016)
- [Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids](https://mlsanity.com/paper/1904.09970/) (2019)
- [Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation](https://mlsanity.com/paper/2411.02293/) (2024)
- [3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks](https://mlsanity.com/paper/1708.01648/) (2017)
- [Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Search](https://mlsanity.com/paper/2205.02961/) (2022)
- [HoloPart: Generative 3D Part Amodal Segmentation](https://mlsanity.com/paper/2504.07943/) (2025)
- [Im2Struct: Recovering 3D Shape Structure from a Single RGB Image](https://mlsanity.com/paper/1804.05469/) (2018)
- [Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Clouds](https://mlsanity.com/paper/2106.03437/) (2021)
- [Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives](https://mlsanity.com/paper/2307.05473/) (2023)
- [Segment Any Mesh](https://mlsanity.com/paper/2408.13679/) (2024)
- [Deep Parametric Shape Predictions using Distance Fields](https://mlsanity.com/paper/1904.08921/) (2019)
- [Unleashing Vecset Diffusion Model for Fast Shape Generation](https://mlsanity.com/paper/2503.16302/) (2025)
- [Marching-Primitives: Shape Abstraction from Signed Distance Function](https://mlsanity.com/paper/2303.13190/) (2023)
- [Primitive-based Shape Abstraction via Nonparametric Bayesian Inference](https://mlsanity.com/paper/2203.14714/) (2022)
- [PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformers](https://mlsanity.com/paper/2407.13677/) (2024)
- [PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformer](https://mlsanity.com/paper/2505.04622/) (2025)
- [3DGen-Bench: Comprehensive Benchmark Suite for 3D Generative Models](https://mlsanity.com/paper/2503.21745/) (2025)
- [MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generation](https://mlsanity.com/paper/2503.20519/) (2025)
- [Aligning Instance-Semantic Sparse Representation towards Unsupervised Object Segmentation and Shape Abstraction with Repeatable Primitives](https://mlsanity.com/paper/2503.06947/) (2025)

## Built on by (most cited first, 6 of 6)

- [Residual Primitive Fitting of 3D Shapes with SuperFrusta](https://mlsanity.com/paper/2512.09201/) (2025)
- [SuperFlex: Deformable Superquadrics for Point Cloud Decomposition](https://mlsanity.com/paper/2607.01015/) (2026)
- [Learning Convex Decomposition via Feature Fields](https://mlsanity.com/paper/2603.09285/) (2026)
- [Prompting Image Generators for Training-free Primitive Shape Abstraction](https://mlsanity.com/paper/2607.05568/) (2026)
- [Hi-TOPS: Hierarchical Topology-aware Scoring Prior for 3D Part Decomposition](https://mlsanity.com/paper/2608.00767/) (2026)
- [Organize Primitives into Semantic Parts: Reinforcement Reasoning for 3D Segmentation](https://mlsanity.com/paper/2610.04602/) (2026)

## Abstract (arXiv)

In user-generated-content (UGC) applications, non-expert users often rely on image-to-3D generative models to create 3D assets. In this context, primitive-based shape abstraction offers a promising solution for UGC scenarios by compressing high-resolution meshes into compact, editable representations. Towards this end, effective shape abstraction must therefore be structure-aware, characterized by low overlap between primitives, part-aware alignment, and primitive compactness. We present Light-SQ, a novel superquadric-based optimization framework that explicitly emphasizes structure-awareness from three aspects. (a) We introduce SDF carving to iteratively udpate the target signed distance field, discouraging overlap between primitives. (b) We propose a block-regrow-fill strategy guided by structure-aware volumetric decomposition, enabling structural partitioning to drive primitive placement. (c) We implement adaptive residual pruning based on SDF update history to surpress over-segmentation and ensure compact results. In addition, Light-SQ supports multiscale fitting, enabling localized refinement to preserve fine geometric details. To evaluate our method, we introduce 3DGen-Prim, a benchmark extending 3DGen-Bench with new metrics for both reconstruction quality and primitive-level editability. Extensive experiments demonstrate that Light-SQ enables efficient, high-fidelity, and editable shape abstraction with superquadrics for complex generated geometry, advancing the feasibility of 3D UGC creation.