# Learning to Generate 3D Shapes from a Single Example

arXiv: https://arxiv.org/abs/2208.02946 · HTML: https://mlsanity.com/paper/2208.02946/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 81 references that are in the map.
- First posted on arXiv 5 Aug 2022.

## Builds on (most cited first, 30 of 43)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows](https://mlsanity.com/paper/1906.12320/) (2019)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [Text2Mesh: Text-Driven Neural Stylization for Meshes](https://mlsanity.com/paper/2112.03221/) (2021)
- [DeepCAD: A Deep Generative Network for Computer-Aided Design Models](https://mlsanity.com/paper/2105.09492/) (2021)
- [PolyGen: An Autoregressive Generative Model of 3D Meshes](https://mlsanity.com/paper/2002.10880/) (2020)
- [Learning Gradient Fields for Shape Generation](https://mlsanity.com/paper/2008.06520/) (2020)
- [Swapping Autoencoder for Deep Image Manipulation](https://mlsanity.com/paper/2007.00653/) (2020)
- [BSP-Net: Generating Compact Meshes via Binary Space Partitioning](https://mlsanity.com/paper/1911.06971/) (2019)
- [PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes](https://mlsanity.com/paper/1911.10949/) (2019)
- [Learning Deformable Tetrahedral Meshes for 3D Reconstruction](https://mlsanity.com/paper/2011.01437/) (2020)
- [SolidGen: An Autoregressive Model for Direct B-rep Synthesis](https://mlsanity.com/paper/2203.13944/) (2022)
- [Improved Techniques for Training Single-Image GANs](https://mlsanity.com/paper/2003.11512/) (2020)
- [Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations](https://mlsanity.com/paper/2205.02825/) (2022)
- [Positional Encoding as Spatial Inductive Bias in GANs](https://mlsanity.com/paper/2012.05217/) (2020)
- [Non-Stationary Texture Synthesis by Adversarial Expansion](https://mlsanity.com/paper/1805.04487/) (2018)
- [Deep Geometric Texture Synthesis](https://mlsanity.com/paper/2007.00074/) (2020)
- [Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models](https://mlsanity.com/paper/2103.15545/) (2021)

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

- [Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models](https://mlsanity.com/paper/2212.14704/) (2022)
- [Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2307.11335/) (2023)
- [Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation](https://mlsanity.com/paper/2303.07937/) (2023)
- [Advances in 3D Generation: A Survey](https://mlsanity.com/paper/2401.17807/) (2024)
- [SinDDM: A Single Image Denoising Diffusion Model](https://mlsanity.com/paper/2211.16582/) (2022)
- [RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model](https://mlsanity.com/paper/2309.00810/) (2023)
- [Implicit Neural Spatial Representations for Time-dependent PDEs](https://mlsanity.com/paper/2210.00124/) (2022)
- [Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape](https://mlsanity.com/paper/2305.15399/) (2023)
- [Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion](https://mlsanity.com/paper/2409.11406/) (2024)
- [NuiScene: Exploring Efficient Generation of Unbounded Outdoor Scenes](https://mlsanity.com/paper/2503.16375/) (2025)
- [Patch-based 3D Natural Scene Generation from a Single Example](https://mlsanity.com/paper/2304.12670/) (2023)
- [ThemeStation: Generating Theme-Aware 3D Assets from Few Exemplars](https://mlsanity.com/paper/2403.15383/) (2024)
- [ShaDDR: Interactive Example-Based Geometry and Texture Generation via 3D Shape Detailization and Differentiable Rendering](https://mlsanity.com/paper/2306.04889/) (2023)
- [SinGRAF: Learning a 3D Generative Radiance Field for a Single Scene](https://mlsanity.com/paper/2211.17260/) (2022)
- [Progressive Text-to-3D Generation for Automatic 3D Prototyping](https://mlsanity.com/paper/2309.14600/) (2023)
- [Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluation](https://mlsanity.com/paper/2403.01619/) (2024)
- [Neural Processing of Tri-Plane Hybrid Neural Fields](https://mlsanity.com/paper/2310.01140/) (2023)
- [DECOLLAGE: 3D Detailization by Controllable, Localized, and Learned Geometry Enhancement](https://mlsanity.com/paper/2409.06129/) (2024)
- [Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation](https://mlsanity.com/paper/2412.09428/) (2024)
- [SYM3D: Learning Symmetric Triplanes for Better 3D-Awareness of GANs](https://mlsanity.com/paper/2406.06432/) (2024)
- [PEGAsus: 3D Personalization of Geometry and Appearance](https://mlsanity.com/paper/2602.08198/) (2026)
- [Retargeting Visual Data with Deformation Fields](https://mlsanity.com/paper/2311.13297/) (2023)
- [Towards Realistic Example-based Modeling via 3D Gaussian Stitching](https://mlsanity.com/paper/2408.15708/) (2024)
- [ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusion](https://mlsanity.com/paper/2502.02187/) (2025)
- [TriTex: Learning Texture from a Single Mesh via Triplane Semantic Features](https://mlsanity.com/paper/2503.16630/) (2025)
- [RefAny3D: 3D Asset-Referenced Diffusion Models for Image Generation](https://mlsanity.com/paper/2601.22094/) (2026)
- [GOEmbed: Gradient Origin Embeddings for Representation Agnostic 3D Feature Learning](https://mlsanity.com/paper/2312.08744/) (2023)
- [ExCellGen: Fast, Controllable, Photorealistic 3D Scene Generation from a Single Real-World Exemplar](https://mlsanity.com/paper/2412.16253/) (2024)
- [ArchComplete: Autoregressive 3D Architectural Design Generation with Hierarchical Diffusion-Based Upsampling](https://mlsanity.com/paper/2412.17957/) (2024)
- [3D Shape Generation: A Survey](https://mlsanity.com/paper/2506.22678/) (2025)

## Abstract (arXiv)

Existing generative models for 3D shapes are typically trained on a large 3D dataset, often of a specific object category. In this paper, we investigate the deep generative model that learns from only a single reference 3D shape. Specifically, we present a multi-scale GAN-based model designed to capture the input shape's geometric features across a range of spatial scales. To avoid large memory and computational cost induced by operating on the 3D volume, we build our generator atop the tri-plane hybrid representation, which requires only 2D convolutions. We train our generative model on a voxel pyramid of the reference shape, without the need of any external supervision or manual annotation. Once trained, our model can generate diverse and high-quality 3D shapes possibly of different sizes and aspect ratios. The resulting shapes present variations across different scales, and at the same time retain the global structure of the reference shape. Through extensive evaluation, both qualitative and quantitative, we demonstrate that our model can generate 3D shapes of various types.