mlsanityData to 7 Oct 2026

PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attention

arXiv 1810.05591 ↗First posted 12 Oct 2018cs.CVcited by 105

Not on the map. Why?

Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Generating 3D point clouds is challenging yet highly desired. This work presents a novel autoregressive model, PointGrow, which can generate diverse and realistic point cloud samples from scratch or conditioned on semantic contexts. This model operates recurrently, with each point sampled according to a conditional distribution given its previously-generated points, allowing inter-point correlations to be well-exploited and 3D shape generative processes to be better interpreted. Since point cloud object shapes are typically encoded by long-range dependencies, we augment our model with dedicated self-attention modules to capture such relations. Extensive evaluations show that PointGrow achieves satisfying performance on both unconditional and conditional point cloud generation tasks, with respect to realism and diversity. Several important applications, such as unsupervised feature learning and shape arithmetic operations, are also demonstrated.

Key facts. Cited by 105 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 22; 2023: 19; 2024: 24; 2025: 14; 2026: 5.

105 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. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  5. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228
  6. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  7. 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 111
  8. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  9. 20223DILG: Irregular Latent Grids for 3D Generative Modelingcited by 92
  10. 2022SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generationcited by 92
  11. 2022Learning to Generate Realistic LiDAR Point Cloudscited by 91
  12. 2023TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Modelscited by 86
38 more
  1. 2022Towards Implicit Text-Guided 3D Shape Generationcited by 68
  2. 20223D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Modelscited by 67
  3. 2023SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulationcited by 66
  4. 2024Advances in 3D Generation: A Surveycited by 62
  5. 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
  6. 2021Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learningcited by 52
  7. 2021Point-set Distances for Learning Representations of 3D Point Cloudscited by 48
  8. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generationcited by 45
  9. 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
  10. 2021Octree Transformer: Autoregressive 3D Shape Generation on Hierarchically Structured Sequencescited by 38
  11. 2022Autoregressive 3D Shape Generation via Canonical Mappingcited by 37
  12. 2021Top-N: Equivariant set and graph generation without exchangeabilitycited by 36
  13. 2023DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusioncited by 32
  14. 2021Orienting Point Clouds with Dipole Propagationcited by 31
  15. 2025OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generationcited by 27
  16. 2024Make-A-Shape: a Ten-Million-scale 3D Shape Modelcited by 25
  17. 2023GECCO: Geometrically-Conditioned Point Diffusion Modelscited by 24
  18. 2021Learning to Generate 3D Shapes with Generative Cellular Automatacited by 22
  19. 2022CSDN: Cross-modal Shape-transfer Dual-refinement Network for Point Cloud Completioncited by 22
  20. 2021SP-GAN: Sphere-Guided 3D Shape Generation and Manipulationcited by 21
  21. 20243D Mesh Editing using Masked LRMscited by 17
  22. 2021Go with the Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstructioncited by 16
  23. 2024Atlas Gaussians Diffusion for 3D Generationcited by 15
  24. 2024NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generationcited by 13
  25. 2021Progressive Seed Generation Auto-encoder for Unsupervised Point Cloud Learningcited by 12
  26. 20233D VR Sketch Guided 3D Shape Prototyping and Explorationcited by 12
  27. 2023Pushing the Limits of 3D Shape Generation at Scalecited by 11
  28. 2023U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Cloudscited by 11
  29. 2023MinD-3D: Reconstruct High-quality 3D objects in Human Braincited by 11
  30. 2024On permutation-invariant neural networkscited by 10
  31. 2024Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodingscited by 10
  32. 20243D Shape Tokenization via Latent Flow Matchingcited by 10
  33. 2023FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generationcited by 9
  34. 2025PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Predictioncited by 9
  35. 2021Attention-based Transformation from Latent Features to Point Cloudscited by 8
  36. 2022Visualizing Global Explanations of Point Cloud DNNscited by 8
  37. 2023Lidar Upsampling with Sliced Wasserstein Distancecited by 8
  38. 2023Towards Controllable Diffusion Models via Reward-Guided Explorationcited by 8

50 most cited of 105 All 105 (JSON)