mlsanityData to 14 Oct 2026

Learning to Generate 3D Shapes from a Single Example

arXiv 2208.02946 ↗First posted 5 Aug 2022cs.GR cs.AI cs.CVcited by 31

Not on the map. Why?

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.

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

43 of 81 references.

References · 43

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  6. 2017Improved Training of Wasserstein GANscited by 2,235
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  8. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  9. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  10. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  11. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  12. 2020Convolutional Occupancy Networkscited by 761
31 more
  1. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  2. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 488
  3. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  4. 2021Text2Mesh: Text-Driven Neural Stylization for Meshescited by 334
  5. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 271
  6. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 269
  7. 2020Learning Gradient Fields for Shape Generationcited by 245
  8. 2020Swapping Autoencoder for Deep Image Manipulationcited by 215
  9. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 206
  10. 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 119
  11. 2020Learning Deformable Tetrahedral Meshes for 3D Reconstructioncited by 85
  12. 2022SolidGen: An Autoregressive Model for Direct B-rep Synthesiscited by 80
  13. 2020Improved Techniques for Training Single-Image GANscited by 78
  14. 2022Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representationscited by 71
  15. 2020Positional Encoding as Spatial Inductive Bias in GANscited by 69
  16. 2018Non-Stationary Texture Synthesis by Adversarial Expansioncited by 67
  17. 2020Deep Geometric Texture Synthesiscited by 51
  18. 2021Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Modelscited by 51
  19. 2020Neural Subdivisioncited by 49
  20. 2020Adversarial Generation of Continuous Implicit Shape Representationscited by 46
  21. 2020DECOR-GAN: 3D Shape Detailization by Conditional Refinementcited by 45
  22. 2021Learning Generative Models of Textured 3D Meshes from Real-World Imagescited by 44
  23. 2020Point2Mesh: A Self-Prior for Deformable Meshescited by 41
  24. 2019A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Imagescited by 37
  25. 2020Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design Sequencescited by 36
  26. 2018Multi-chart Generative Surface Modelingcited by 26
  27. 2020P-Cloth: Interactive Complex Cloth Simulation on Multi-GPU Systems using Dynamic Matrix Assembly and Pipelined Implicit Integratorscited by 26
  28. 2021Toward Spatially Unbiased Generative Modelscited by 17
  29. 2021Catch-A-Waveform: Learning to Generate Audio from a Single Short Examplecited by 15
  30. 2021Diverse Generation from a Single Video Made Possiblecited by 13
  31. 2020TM-NET: Deep Generative Networks for Textured Meshescited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 10; 2024: 10; 2025: 5; 2026: 2.

31 papers.

Sort:

By area:

  1. 2022Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Modelscited by 151
  2. 2023Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fieldscited by 143
  3. 2023Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generationcited by 133
  4. 2024Advances in 3D Generation: A Surveycited by 63
  5. 2022SinDDM: A Single Image Denoising Diffusion Modelcited by 60
  6. 2023RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Modelcited by 47
  7. 2022Implicit Neural Spatial Representations for Time-dependent PDEscited by 35
  8. 2023Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shapecited by 29
  9. 2024Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusioncited by 19
  10. 2025NuiScene: Exploring Efficient Generation of Unbounded Outdoor Scenescited by 19
  11. 2023Patch-based 3D Natural Scene Generation from a Single Examplecited by 15
  12. 2024ThemeStation: Generating Theme-Aware 3D Assets from Few Exemplarscited by 14
19 more
  1. 2023ShaDDR: Interactive Example-Based Geometry and Texture Generation via 3D Shape Detailization and Differentiable Renderingcited by 13
  2. 2022SinGRAF: Learning a 3D Generative Radiance Field for a Single Scenecited by 11
  3. 2023Progressive Text-to-3D Generation for Automatic 3D Prototypingcited by 9
  4. 2024Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluationcited by 9
  5. 2023Neural Processing of Tri-Plane Hybrid Neural Fieldscited by 8
  6. 2024DECOLLAGE: 3D Detailization by Controllable, Localized, and Learned Geometry Enhancementcited by 7
  7. 2024Multimodal Music Generation with Explicit Bridges and Retrieval Augmentationcited by 6
  8. 2024SYM3D: Learning Symmetric Triplanes for Better 3D-Awareness of GANscited by 5
  9. 2026PEGAsus: 3D Personalization of Geometry and Appearancecited by 5
  10. 2023Retargeting Visual Data with Deformation Fieldscited by 3
  11. 2024Towards Realistic Example-based Modeling via 3D Gaussian Stitchingcited by 3
  12. 2025ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusioncited by 3
  13. 2025TriTex: Learning Texture from a Single Mesh via Triplane Semantic Featurescited by 2
  14. 2026RefAny3D: 3D Asset-Referenced Diffusion Models for Image Generationcited by 2
  15. 2023GOEmbed: Gradient Origin Embeddings for Representation Agnostic 3D Feature Learningcited by 1
  16. 2024ExCellGen: Fast, Controllable, Photorealistic 3D Scene Generation from a Single Real-World Exemplarcited by 0
  17. 2024ArchComplete: Autoregressive 3D Architectural Design Generation with Hierarchical Diffusion-Based Upsamplingcited by 0
  18. 20253D Shape Generation: A Surveycited by 0
  19. 2025Three-Dimensional Anatomical Data Generation Based on Artificial Neural Networkscited by 0