mlsanityData to 14 Oct 2026

PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows

arXiv 1906.12320 ↗First posted 28 Jun 2019cs.CV cs.LGcited by 488

Not on the map. Why?

Cited by 127 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

As 3D point clouds become the representation of choice for multiple vision and graphics applications, the ability to synthesize or reconstruct high-resolution, high-fidelity point clouds becomes crucial. Despite the recent success of deep learning models in discriminative tasks of point clouds, generating point clouds remains challenging. This paper proposes a principled probabilistic framework to generate 3D point clouds by modeling them as a distribution of distributions. Specifically, we learn a two-level hierarchy of distributions where the first level is the distribution of shapes and the second level is the distribution of points given a shape. This formulation allows us to both sample shapes and sample an arbitrary number of points from a shape. Our generative model, named PointFlow, learns each level of the distribution with a continuous normalizing flow. The invertibility of normalizing flows enables the computation of the likelihood during training and allows us to train our model in the variational inference framework. Empirically, we demonstrate that PointFlow achieves state-of-the-art performance in point cloud generation. We additionally show that our model can faithfully reconstruct point clouds and learn useful representations in an unsupervised manner. The code will be available at https://github.com/stevenygd/PointFlow.

Key facts. Cited by 488 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 80; 2022: 81; 2023: 104; 2024: 85; 2025: 80; 2026: 58.

488 papers.

Sort:

By area:

  1. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  2. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  3. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  4. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 699
  5. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  6. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  7. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 553
  8. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  9. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 516
  10. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  11. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 458
  12. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
38 more
  1. 2023Shap-E: Generating Conditional 3D Implicit Functionscited by 385
  2. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
  3. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 326
  4. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  5. 2022Diffusion Models for Medical Image Analysis: A Comprehensive Surveycited by 273
  6. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 271
  7. 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 270
  8. 2023Holodeck: Language Guided Generation of 3D Embodied AI Environmentscited by 268
  9. 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 259
  10. 2021CLIP-Forge: Towards Zero-Shot Text-to-Shape Generationcited by 254
  11. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 231
  12. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusioncited by 204
  13. 2023MeshDiffusion: Score-based Generative 3D Mesh Modelingcited by 199
  14. 2023XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchiescited by 189
  15. 2021Shape As Points: A Differentiable Poisson Solvercited by 187
  16. 2021Low-Light Image Enhancement with Normalizing Flowcited by 185
  17. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  18. 2023DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Modelscited by 154
  19. 2024GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generationcited by 153
  20. 2022Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Modelscited by 151
  21. 2022Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functionscited by 133
  22. 2023Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generationcited by 133
  23. 2022Neural Wavelet-domain Diffusion for 3D Shape Generationcited by 132
  24. 2024Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiTcited by 132
  25. 2023Locally Attentional SDF Diffusion for Controllable 3D Shape Generationcited by 130
  26. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  27. 2023Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fieldscited by 123
  28. 2024CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refinercited by 123
  29. 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 112
  30. 2023DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generationcited by 110
  31. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 106
  32. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 103
  33. 2021Holistic 3D Scene Understanding from a Single Image with Implicit Representationcited by 94
  34. 2022Learning to Generate Realistic LiDAR Point Cloudscited by 93
  35. 2022POCO: Point Convolution for Surface Reconstructioncited by 92
  36. 2022SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generationcited by 92
  37. 2025Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modelingcited by 89
  38. 2023TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Modelscited by 87

50 most cited of 488 All 488 (JSON)