mlsanityData to 7 Oct 2026

3D Shape Generation and Completion through Point-Voxel Diffusion

arXiv 2104.03670 ↗First posted 8 Apr 2021cs.CVcited by 516

Not on the map. Why?

Cited by 271 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose a novel approach for probabilistic generative modeling of 3D shapes. Unlike most existing models that learn to deterministically translate a latent vector to a shape, our model, Point-Voxel Diffusion (PVD), is a unified, probabilistic formulation for unconditional shape generation and conditional, multi-modal shape completion. PVD marries denoising diffusion models with the hybrid, point-voxel representation of 3D shapes. It can be viewed as a series of denoising steps, reversing the diffusion process from observed point cloud data to Gaussian noise, and is trained by optimizing a variational lower bound to the (conditional) likelihood function. Experiments demonstrate that PVD is capable of synthesizing high-fidelity shapes, completing partial point clouds, and generating multiple completion results from single-view depth scans of real objects.

Key facts. Cited by 516 papers in the map (data through 7 Oct 2026). Builds on 38 of its 49 references that are in the map. First posted on arXiv 8 Apr 2021.

Builds on

38 of 49 references.

References · 38

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Denoising Diffusion Implicit Modelscited by 9,655
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  8. 2016Density estimation using Real NVPcited by 2,029
  9. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  10. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  11. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  12. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
26 more
  1. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  2. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  3. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  4. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  5. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  6. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  7. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  8. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  9. 2020Learning Gradient Fields for Shape Generationcited by 245
  10. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  11. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  12. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  13. 2019Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Modelcited by 147
  14. 2019Morphing and Sampling Network for Dense Point Cloud Completioncited by 132
  15. 2016Generative and Discriminative Voxel Modeling with Convolutional Neural Networkscited by 128
  16. 2018PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attentioncited by 105
  17. 2020SoftFlow: Probabilistic Framework for Normalizing Flow on Manifoldscited by 97
  18. 2018Multiresolution Tree Networks for 3D Point Cloud Processingcited by 91
  19. 2020Discrete Point Flow Networks for Efficient Point Cloud Generationcited by 87
  20. 2018Point Cloud GANcited by 79
  21. 2016A Large Dataset of Object Scanscited by 64
  22. 2020Multimodal Shape Completion via Conditional Generative Adversarial Networkscited by 61
  23. 2018Learning to Reconstruct Shapes from Unseen Classescited by 60
  24. 2018Learning Descriptor Networks for 3D Shape Synthesis and Analysiscited by 56
  25. 2018VoxSegNet: Volumetric CNNs for Semantic Part Segmentation of 3D Shapescited by 37
  26. 2017DeformNet: Free-Form Deformation Network for 3D Shape Reconstruction from a Single Imagecited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 68; 2023: 167; 2024: 141; 2025: 89; 2026: 45.

516 papers.

Sort:

By area:

  1. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  2. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  3. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  4. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,023
  5. 2022Diffusion Models in Vision: A Surveycited by 1,008
  6. 2023Training Diffusion Models with Reinforcement Learningcited by 939
  7. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  8. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  9. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 684
  10. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
  11. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 619
  12. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 567
38 more
  1. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  2. 2024Latte: Latent Diffusion Transformer for Video Generationcited by 536
  3. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  4. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  5. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  6. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 421
  7. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
  8. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 365
  9. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 359
  10. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 331
  11. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  12. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  13. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
  14. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 287
  15. 20223D Neural Field Generation using Triplane Diffusioncited by 274
  16. 2023Holodeck: Language Guided Generation of 3D Embodied AI Environmentscited by 257
  17. 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 254
  18. 2024StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generationcited by 240
  19. 2022A Survey on Generative Diffusion Modelcited by 238
  20. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusioncited by 230
  21. 2022Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problemcited by 229
  22. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228
  23. 2022Dual Diffusion Implicit Bridges for Image-to-Image Translationcited by 212
  24. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  25. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusioncited by 204
  26. 2023Scalable 3D Captioning with Pretrained Modelscited by 201
  27. 2022SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Controlcited by 191
  28. 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 184
  29. 2023XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchiescited by 183
  30. 2021A Variational Perspective on Diffusion-Based Generative Models and Score Matchingcited by 182
  31. 20233DGen: Triplane Latent Diffusion for Textured Mesh Generationcited by 181
  32. 2021On Fast Sampling of Diffusion Probabilistic Modelscited by 170
  33. 2023Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Modelscited by 169
  34. 2022Generative Modelling With Inverse Heat Dissipationcited by 164
  35. 2022RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generationcited by 162
  36. 2023DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesiscited by 159
  37. 2025Native and Compact Structured Latents for 3D Generationcited by 157
  38. 2022NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priorscited by 156

50 most cited of 516 All 516 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Evaluating Latent Generative Paradigms for High-Fidelity 3D Shape Completion from a Single Depth Image
  2. 2025Repurposing 2D Diffusion Models for 3D Shape Completion
  3. 2024Part-aware Shape Generation with Latent 3D Diffusion of Neural Voxel Fields
  4. 2025Point-Based Shape Representation Generation with a Correspondence-Preserving Diffusion Model
  5. 2024GEM3D: GEnerative Medial Abstractions for 3D Shape Synthesis
  6. 2023Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape
  7. 2026BuildAnyPoint: 3D Building Structured Abstraction from Diverse Point Clouds
  8. 2023MeshDiffusion: Score-based Generative 3D Mesh Modeling