mlsanityData to 14 Oct 2026

Enhancing Diffusion-based Point Cloud Generation with Smoothness Constraint

arXiv 2404.02396 ↗First posted 3 Apr 2024cs.CV cs.GR cs.LGcited by 5

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

Abstract (arXiv)

Diffusion models have been popular for point cloud generation tasks. Existing works utilize the forward diffusion process to convert the original point distribution into a noise distribution and then learn the reverse diffusion process to recover the point distribution from the noise distribution. However, the reverse diffusion process can produce samples with non-smooth points on the surface because of the ignorance of the point cloud geometric properties. We propose alleviating the problem by incorporating the local smoothness constraint into the diffusion framework for point cloud generation. Experiments demonstrate the proposed model can generate realistic shapes and smoother point clouds, outperforming multiple state-of-the-art methods.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 24 of its 32 references that are in the map. First posted on arXiv 3 Apr 2024.

Builds on

24 of 32 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Diffusion Probabilistic Models for 3D Point Cloud Generation2 Mar

Other references · 23

  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  5. 2021Score-based Generative Modeling in Latent Spacecited by 636
  6. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  7. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  8. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  9. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 504
  10. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 488
  11. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 463
  12. 2020Learning Gradient Fields for Shape Generationcited by 245
11 more
  1. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  2. 2021Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Imagescited by 113
  3. 2018PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attentioncited by 105
  4. 2020SoftFlow: Probabilistic Framework for Normalizing Flow on Manifoldscited by 98
  5. 2019Interpolated Convolutional Networks for 3D Point Cloud Understandingcited by 86
  6. 2018Point Cloud GANcited by 79
  7. 2021SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Cloudscited by 64
  8. 2018A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Drivingcited by 54
  9. 20183D Point Cloud Denoising using Graph Laplacian Regularization of a Low Dimensional Manifold Modelcited by 47
  10. 2022NVDiff: Graph Generation through the Diffusion of Node Vectorscited by 18
  11. 2023A Hierarchical Spatial Transformer for Massive Point Samples in Continuous Spacecited by 10

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 4.

5 papers.

  1. 2025Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agentscited by 38
  2. 2025NeRF-Based defect detectioncited by 7
  3. 2024Irregularity Inspection using Neural Radiance Fieldcited by 2
  4. 2025Incorporating Inductive Biases to Energy-based Generative Modelscited by 1
  5. 2025Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updatescited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Point Cloud Resampling with Learnable Heat Diffusion
  2. 2022Fast Point Cloud Generation with Straight Flows
  3. 2023FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generation
  4. 2024Efficient and Scalable Point Cloud Generation with Sparse Point-Voxel Diffusion Models
  5. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion
  6. 2023PCRDiffusion: Diffusion Probabilistic Models for Point Cloud Registration
  7. 2025Guided and Unguided Conditional Diffusion Mechanisms for Structured and Semantically-Aware 3D Point Cloud Generation
  8. 2023BuilDiff: 3D Building Shape Generation using Single-Image Conditional Point Cloud Diffusion Models