# Parameterize Structure with Differentiable Template for 3D Shape Generation

arXiv: https://arxiv.org/abs/2410.10399 · HTML: https://mlsanity.com/paper/2410.10399/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 62 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Builds on (most cited first, 20 of 20)

- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation](https://mlsanity.com/paper/2212.04493/) (2022)
- [AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation](https://mlsanity.com/paper/2203.09516/) (2022)
- [Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings](https://mlsanity.com/paper/1803.08495/) (2018)
- [PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes](https://mlsanity.com/paper/1911.10949/) (2019)
- [SDM-NET: Deep Generative Network for Structured Deformable Mesh](https://mlsanity.com/paper/1908.04520/) (2019)
- [POCO: Point Convolution for Surface Reconstruction](https://mlsanity.com/paper/2201.01831/) (2022)
- [SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulation](https://mlsanity.com/paper/2303.12236/) (2023)
- [Surface Reconstruction from Point Clouds by Learning Predictive Context Priors](https://mlsanity.com/paper/2204.11015/) (2022)
- [Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives](https://mlsanity.com/paper/2307.05473/) (2023)
- [PointGMM: a Neural GMM Network for Point Clouds](https://mlsanity.com/paper/2003.13326/) (2020)
- [DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation](https://mlsanity.com/paper/2008.05440/) (2020)
- [GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation](https://mlsanity.com/paper/2211.16762/) (2022)
- [ShapeCoder: Discovering Abstractions for Visual Programs from Unstructured Primitives](https://mlsanity.com/paper/2305.05661/) (2023)
- [Parsing Geometry Using Structure-Aware Shape Templates](https://mlsanity.com/paper/1808.01337/) (2018)
- [PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformers](https://mlsanity.com/paper/2407.13677/) (2024)

## Built on by (most cited first, 1 of 1)

- [SPARK: Sim-ready Part-level Articulated Reconstruction with VLM Knowledge](https://mlsanity.com/paper/2512.01629/) (2025)

## Abstract (arXiv)

Structural representation is crucial for reconstructing and generating editable 3D shapes with part semantics. Recent 3D shape generation works employ complicated networks and structure definitions relying on hierarchical annotations and pay less attention to the details inside parts. In this paper, we propose the method that parameterizes the shared structure in the same category using a differentiable template and corresponding fixed-length parameters. Specific parameters are fed into the template to calculate cuboids that indicate a concrete shape. We utilize the boundaries of three-view drawings of each cuboid to further describe the inside details. Shapes are represented with the parameters and three-view details inside cuboids, from which the SDF can be calculated to recover the object. Benefiting from our fixed-length parameters and three-view details, our networks for reconstruction and generation are simple and effective to learn the latent space. Our method can reconstruct or generate diverse shapes with complicated details, and interpolate them smoothly. Extensive evaluations demonstrate the superiority of our method on reconstruction from point cloud, generation, and interpolation.