mlsanityData to 7 Oct 2026

Diffusion Probabilistic Models for 3D Point Cloud Generation

arXiv 2103.01458 ↗First posted 2 Mar 2021cs.CVcited by 734

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

We present a probabilistic model for point cloud generation, which is fundamental for various 3D vision tasks such as shape completion, upsampling, synthesis and data augmentation. Inspired by the diffusion process in non-equilibrium thermodynamics, we view points in point clouds as particles in a thermodynamic system in contact with a heat bath, which diffuse from the original distribution to a noise distribution. Point cloud generation thus amounts to learning the reverse diffusion process that transforms the noise distribution to the distribution of a desired shape. Specifically, we propose to model the reverse diffusion process for point clouds as a Markov chain conditioned on certain shape latent. We derive the variational bound in closed form for training and provide implementations of the model. Experimental results demonstrate that our model achieves competitive performance in point cloud generation and auto-encoding. The code is available at urlhttps://github.com/luost26/diffusion-point-cloud.

Key facts. Cited by 734 papers in the map (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 19 of its 27 references that are in the map. First posted on arXiv 2 Mar 2021.

Builds on

19 of 27 references.

References · 19

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  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. 2018Neural Ordinary Differential Equationscited by 3,733
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2015Variational Inference with Normalizing Flowscited by 2,161
  10. 2016Density estimation using Real NVPcited by 2,029
  11. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 584
  12. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
7 more
  1. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  2. 2020Learning Gradient Fields for Shape Generationcited by 245
  3. 2016Variational Lossy Autoencodercited by 175
  4. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  5. 2018PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attentioncited by 105
  6. 2018Multiresolution Tree Networks for 3D Point Cloud Processingcited by 91
  7. 2020Discrete Point Flow Networks for Efficient Point Cloud Generationcited by 87

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 89; 2023: 197; 2024: 198; 2025: 146; 2026: 86.

734 papers.

Sort:

By area:

  1. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  2. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  3. 2022Human Motion Diffusion Modelcited by 1,062
  4. 2022Diffusion Models in Vision: A Surveycited by 1,008
  5. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  6. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  7. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 695
  8. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  9. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
  10. 2021Score-based Generative Modeling in Latent Spacecited by 634
  11. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
  12. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
38 more
  1. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  2. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 515
  3. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 511
  4. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  5. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 447
  6. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  7. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  8. 2023Shap-E: Generating Conditional 3D Implicit Functionscited by 379
  9. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
  10. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 365
  11. 2023DeepCache: Accelerating Diffusion Models for Freecited by 346
  12. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  13. 2022Novel View Synthesis with Diffusion Modelscited by 299
  14. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 287
  15. 20223D Neural Field Generation using Triplane Diffusioncited by 274
  16. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 273
  17. 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 268
  18. 2023GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Modelscited by 255
  19. 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 254
  20. 2022A Survey on Generative Diffusion Modelcited by 238
  21. 2022Diffusion Probabilistic Modeling for Video Generationcited by 237
  22. 2023Diffusion-based Generation, Optimization, and Planning in 3D Scenescited by 237
  23. 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Modelscited by 234
  24. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusioncited by 230
  25. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228
  26. 2022MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesiscited by 218
  27. 2022Structure-based Drug Design with Equivariant Diffusion Modelscited by 213
  28. 2022Dual Diffusion Implicit Bridges for Image-to-Image Translationcited by 212
  29. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusioncited by 204
  30. 2023A Survey on Video Diffusion Modelscited by 203
  31. 2023One Transformer Fits All Distributions in Multi-Modal Diffusion at Scalecited by 185
  32. 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 184
  33. 2023XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchiescited by 183
  34. 2022Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Qualitycited by 181
  35. 20233DGen: Triplane Latent Diffusion for Textured Mesh Generationcited by 181
  36. 2023Video Probabilistic Diffusion Models in Projected Latent Spacecited by 171
  37. 2021On Fast Sampling of Diffusion Probabilistic Modelscited by 170
  38. 2023Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Modelscited by 169

50 most cited of 734 All 734 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Point Cloud Resampling with Learnable Heat Diffusion
  2. 2025Consistency Diffusion Models for Single-Image 3D Reconstruction with Priors
  3. 2025PDT: Point Distribution Transformation with Diffusion Models
  4. 2025NnD: Diffusion-based Generation of Physically-Nonnegative Objects
  5. 2024ComPC: Completing a 3D Point Cloud with 2D Diffusion Priors
  6. 2024Diffusion Models in 3D Vision: A Survey
  7. 2023LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models
  8. 2025RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learning