mlsanityData to 7 Oct 2026

Discrete Point Flow Networks for Efficient Point Cloud Generation

arXiv 2007.10170 ↗First posted 20 Jul 2020cs.CVcited by 87

Not on the map. Why?

Cited by 33 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Generative models have proven effective at modeling 3D shapes and their statistical variations. In this paper we investigate their application to point clouds, a 3D shape representation widely used in computer vision for which, however, only few generative models have yet been proposed. We introduce a latent variable model that builds on normalizing flows with affine coupling layers to generate 3D point clouds of an arbitrary size given a latent shape representation. To evaluate its benefits for shape modeling we apply this model for generation, autoencoding, and single-view shape reconstruction tasks. We improve over recent GAN-based models in terms of most metrics that assess generation and autoencoding. Compared to recent work based on continuous flows, our model offers a significant speedup in both training and inference times for similar or better performance. For single-view shape reconstruction we also obtain results on par with state-of-the-art voxel, point cloud, and mesh-based methods.

Key facts. Cited by 87 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 15; 2023: 23; 2024: 14; 2025: 19; 2026: 7.

87 papers.

Sort:

By area:

  1. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  2. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  3. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  4. 2023DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generationcited by 110
  5. 2022SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generationcited by 92
  6. 2023TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Modelscited by 86
  7. 2022Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantificationcited by 71
  8. 2022Towards Implicit Text-Guided 3D Shape Generationcited by 68
  9. 20223D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Modelscited by 67
  10. 2024Advances in 3D Generation: A Surveycited by 62
  11. 2022Fast Point Cloud Generation with Straight Flowscited by 56
  12. 2022Learning Implicit Templates for Point-Based Clothed Human Modelingcited by 50
38 more
  1. 2021Particle Cloud Generation with Message Passing Generative Adversarial Networkscited by 45
  2. 2025SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Imagescited by 41
  3. 2023Controllable Mesh Generation Through Sparse Latent Point Diffusion Modelscited by 40
  4. 2023Sketch and Text Guided Diffusion Model for Colored Point Cloud Generationcited by 36
  5. 2024Wasserstein Flow Matching: Generative modeling over families of distributionscited by 27
  6. 2024Text2LiDAR: Text-guided LiDAR Point Cloud Generation via Equirectangular Transformercited by 26
  7. 20233DQD: Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Processcited by 25
  8. 2023AI-Generated Content (AIGC) for Various Data Modalities: A Surveycited by 25
  9. 2024Make-A-Shape: a Ten-Million-scale 3D Shape Modelcited by 25
  10. 2023GECCO: Geometrically-Conditioned Point Diffusion Modelscited by 24
  11. 2021SP-GAN: Sphere-Guided 3D Shape Generation and Manipulationcited by 21
  12. 2022PD-Flow: A Point Cloud Denoising Framework with Normalizing Flowscited by 19
  13. 2021PU-Flow: a Point Cloud Upsampling Network with Normalizing Flowscited by 17
  14. 2025Not-So-Optimal Transport Flows for 3D Point Cloud Generationcited by 17
  15. 2021Go with the Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstructioncited by 16
  16. 2024PointInfinity: Resolution-Invariant Point Diffusion Modelscited by 15
  17. 2021Progressive Seed Generation Auto-encoder for Unsupervised Point Cloud Learningcited by 12
  18. 2023Pushing the Limits of 3D Shape Generation at Scalecited by 11
  19. 2023SimNP: Learning Self-Similarity Priors Between Neural Pointscited by 11
  20. 2023Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generationcited by 11
  21. 2023Humans as Light Bulbs: 3D Human Reconstruction from Thermal Reflectioncited by 10
  22. 2023MVDD: Multi-View Depth Diffusion Modelscited by 10
  23. 2024Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodingscited by 10
  24. 2023FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generationcited by 9
  25. 2023Fast Training of Diffusion Transformer with Extreme Masking for 3D Point Clouds Generationcited by 9
  26. 2025PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Predictioncited by 9
  27. 2021Attention-based Transformation from Latent Features to Point Cloudscited by 8
  28. 2023Towards Controllable Diffusion Models via Reward-Guided Explorationcited by 8
  29. 2023MVControl: Adding Conditional Control to Multi-view Diffusion for Controllable Text-to-3D Generationcited by 8
  30. 2024Efficient 3D Shape Generation via Diffusion Mamba with Bidirectional SSMscited by 7
  31. 2024Efficient and Scalable Point Cloud Generation with Sparse Point-Voxel Diffusion Modelscited by 7
  32. 2023ET3D: Efficient Text-to-3D Generation via Multi-View Distillationcited by 6
  33. 2024Multi-scale Latent Point Consistency Models for 3D Shape Generationcited by 6
  34. 2025Representing 3D Shapes With 64 Latent Vectors for 3D Diffusion Modelscited by 6
  35. 2022Neural Volumetric Mesh Generatorcited by 5
  36. 2022PointInverter: Point Cloud Reconstruction and Editing via a Generative Model with Shape Priorscited by 5
  37. 2022IC3D: Image-Conditioned 3D Diffusion for Shape Generationcited by 5
  38. 2025Unified Cross-Scale 3D Generation and Understanding via Autoregressive Modelingcited by 5

50 most cited of 87 All 87 (JSON)