# DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation

arXiv: https://arxiv.org/abs/2008.05440 · HTML: https://mlsanity.com/paper/2008.05440/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2020.

## Built on by (most cited first, 30 of 31)

- [Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures](https://mlsanity.com/paper/2211.07600/) (2022)
- [SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation](https://mlsanity.com/paper/2206.12055/) (2022)
- [Towards Implicit Text-Guided 3D Shape Generation](https://mlsanity.com/paper/2203.14622/) (2022)
- [Articulate AnyMesh: Open-Vocabulary 3D Articulated Objects Modeling](https://mlsanity.com/paper/2502.02590/) (2025)
- [DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion](https://mlsanity.com/paper/2305.01921/) (2023)
- [Mesh-based Gaussian Splatting for Real-time Large-scale Deformation](https://mlsanity.com/paper/2402.04796/) (2024)
- [From One to More: Contextual Part Latents for 3D Generation](https://mlsanity.com/paper/2507.08772/) (2025)
- [4Dynamic: Text-to-4D Generation with Hybrid Priors](https://mlsanity.com/paper/2407.12684/) (2024)
- [Semi-Weakly Supervised Object Kinematic Motion Prediction](https://mlsanity.com/paper/2303.17774/) (2023)
- [Topology-Aware Latent Diffusion for 3D Shape Generation](https://mlsanity.com/paper/2401.17603/) (2024)
- [DPF-Net: Combining Explicit Shape Priors in Deformable Primitive Field for Unsupervised Structural Reconstruction of 3D Objects](https://mlsanity.com/paper/2308.13225/) (2023)
- [Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models](https://mlsanity.com/paper/2311.17050/) (2023)
- [CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generation](https://mlsanity.com/paper/2504.19174/) (2025)
- [3D Generative Model Latent Disentanglement via Local Eigenprojection](https://mlsanity.com/paper/2302.12798/) (2023)
- [CoFie: Learning Compact Neural Surface Representations with Coordinate Fields](https://mlsanity.com/paper/2406.03417/) (2024)
- [SeaLion: Semantic Part-Aware Latent Point Diffusion Models for 3D Generation](https://mlsanity.com/paper/2505.17721/) (2025)
- [Text-guided Image-and-Shape Editing and Generation: A Short Survey](https://mlsanity.com/paper/2304.09244/) (2023)
- [Seg&Struct: The Interplay Between Part Segmentation and Structure Inference for 3D Shape Parsing](https://mlsanity.com/paper/2211.00382/) (2022)
- [MotionAnymesh: Physics-Grounded Articulation for Simulation-Ready Digital Twins](https://mlsanity.com/paper/2603.12936/) (2026)
- [LoopDraw: a Loop-Based Autoregressive Model for Shape Synthesis and Editing](https://mlsanity.com/paper/2212.04981/) (2022)
- [3D Semantic Subspace Traverser: Empowering 3D Generative Model with Shape Editing Capability](https://mlsanity.com/paper/2307.14051/) (2023)
- [Intelligent Generation of Graphical Game Assets: A Conceptual Framework and Systematic Review of the State of the Art](https://mlsanity.com/paper/2311.10129/) (2023)
- [StructRe: Rewriting for Structured Shape Modeling](https://mlsanity.com/paper/2311.17510/) (2023)
- [Partial Symmetry Detection for 3D Geometry using Contrastive Learning with Geodesic Point Cloud Patches](https://mlsanity.com/paper/2312.08230/) (2023)
- [Parameterize Structure with Differentiable Template for 3D Shape Generation](https://mlsanity.com/paper/2410.10399/) (2024)
- [BoxSplitGen: A Generative Model for 3D Part Bounding Boxes in Varying Granularity](https://mlsanity.com/paper/2602.20666/) (2026)
- [CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customization](https://mlsanity.com/paper/2603.19121/) (2026)
- [3DLatNav: Navigating Generative Latent Spaces for Semantic-Aware 3D Object Manipulation](https://mlsanity.com/paper/2211.09770/) (2022)
- [Diverse Part Synthesis for 3D Shape Creation](https://mlsanity.com/paper/2401.09384/) (2024)
- [SAR2Struct: Extracting 3D Semantic Structural Representation of Aircraft Targets from Single-View SAR Image](https://mlsanity.com/paper/2506.06757/) (2025)

## Abstract (arXiv)

D shape generation is a fundamental operation in computer graphics. While significant progress has been made, especially with recent deep generative models, it remains a challenge to synthesize high-quality shapes with rich geometric details and complex structure, in a controllable manner. To tackle this, we introduce DSG-Net, a deep neural network that learns a disentangled structured and geometric mesh representation for 3D shapes, where two key aspects of shapes, geometry, and structure, are encoded in a synergistic manner to ensure plausibility of the generated shapes, while also being disentangled as much as possible. This supports a range of novel shape generation applications with disentangled control, such as interpolation of structure (geometry) while keeping geometry (structure) unchanged. To achieve this, we simultaneously learn structure and geometry through variational autoencoders (VAEs) in a hierarchical manner for both, with bijective mappings at each level. In this manner, we effectively encode geometry and structure in separate latent spaces, while ensuring their compatibility: the structure is used to guide the geometry and vice versa. At the leaf level, the part geometry is represented using a conditional part VAE, to encode high-quality geometric details, guided by the structure context as the condition. Our method not only supports controllable generation applications but also produces high-quality synthesized shapes, outperforming state-of-the-art methods. The code has been released at https://github.com/IGLICT/DSG-Net.