mlsanityData to 13 Oct 2026

Orienting Point Clouds with Dipole Propagation

arXiv 2105.01604 ↗First posted 4 May 2021cs.GR cs.CV cs.LGcited by 31

Not on the map. Why?

Abstract (arXiv)

Establishing a consistent normal orientation for point clouds is a notoriously difficult problem in geometry processing, requiring attention to both local and global shape characteristics. The normal direction of a point is a function of the local surface neighborhood; yet, point clouds do not disclose the full underlying surface structure. Even assuming known geodesic proximity, calculating a consistent normal orientation requires the global context. In this work, we introduce a novel approach for establishing a globally consistent normal orientation for point clouds. Our solution separates the local and global components into two different sub-problems. In the local phase, we train a neural network to learn a coherent normal direction per patch (i.e., consistently oriented normals within a single patch). In the global phase, we propagate the orientation across all coherent patches using a dipole propagation. Our dipole propagation decides to orient each patch using the electric field defined by all previously orientated patches. This gives rise to a global propagation that is stable, as well as being robust to nearby surfaces, holes, sharp features and noise.

Key facts. Cited by 31 papers in the map (data through 13 Oct 2026). Builds on 36 of its 73 references that are in the map. First posted on arXiv 4 May 2021.

Builds on

36 of 73 references.

References · 36

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,231
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,389
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,686
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,222
  5. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 976
  6. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  7. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  8. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  9. 2018PCN: Point Completion Networkcited by 383
  10. 2020Learning Gradient Fields for Shape Generationcited by 245
  11. 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 239
  12. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
24 more
  1. 2018PU-Net: Point Cloud Upsampling Networkcited by 209
  2. 2016Thingi10K: A Dataset of 10,000 3D-Printing Modelscited by 182
  3. 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 164
  4. 2019Morphing and Sampling Network for Dense Point Cloud Completioncited by 132
  5. 2018Deep Geometric Prior for Surface Reconstructioncited by 110
  6. 20183D Point Capsule Networkscited by 106
  7. 2020Point Cloud Completion by Skip-attention Network with Hierarchical Foldingcited by 106
  8. 2018PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attentioncited by 105
  9. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  10. 2019PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Cloudscited by 99
  11. 2017PCPNET: Learning Local Shape Properties from Raw Point Cloudscited by 98
  12. 2018EC-Net: an Edge-aware Point set Consolidation Networkcited by 84
  13. 2018Point Cloud GANcited by 79
  14. 2019Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaningcited by 58
  15. 2019RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completioncited by 58
  16. 2020Differentiable Manifold Reconstruction for Point Cloud Denoisingcited by 52
  17. 2020Learning Graph-Convolutional Representations for Point Cloud Denoisingcited by 40
  18. 2020PointGMM: a Neural GMM Network for Point Cloudscited by 33
  19. 2019L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attentioncited by 32
  20. 2020Self-Sampling for Neural Point Cloud Consolidationcited by 15
  21. 2020Point Cloud Completion by Learning Shape Priorscited by 14
  22. 2020Geometric Adversarial Attacks and Defenses on 3D Point Cloudscited by 11
  23. 2018High Fidelity Semantic Shape Completion for Point Clouds using Latent Optimizationcited by 9
  24. 2020Non-Local Part-Aware Point Cloud Denoisingcited by 4

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 3; 2022: 7; 2023: 6; 2024: 5; 2025: 8; 2026: 2.

31 papers.

Sort:

  1. 2021Shape As Points: A Differentiable Poisson Solvercited by 186
  2. 2022CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimizationcited by 46
  3. 2022NeAF: Learning Neural Angle Fields for Point Normal Estimationcited by 38
  4. 2023Robust Zero Level-Set Extraction from Unsigned Distance Fields Based on Double Coveringcited by 21
  5. 2021Neural-IMLS: Self-supervised Implicit Moving Least-Squares Network for Surface Reconstructioncited by 13
  6. 20243D Reconstruction with Fast Dipole Sumscited by 12
  7. 2022PCDNF: Revisiting Learning-based Point Cloud Denoising via Joint Normal Filteringcited by 11
  8. 2023Neural Gradient Learning and Optimization for Oriented Point Normal Estimationcited by 11
  9. 2024MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Stepcited by 11
  10. 2023Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimationcited by 10
  11. 2023NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Functioncited by 10
  12. 2023Deep Internal Learning: Deep Learning from a Single Inputcited by 9
19 more
  1. 2022Deep Surface Reconstruction from Point Clouds with Visibility Informationcited by 8
  2. 2022Point normal orientation and surface reconstruction by incorporating isovalue constraints to Poisson equationcited by 8
  3. 2023Neural Stochastic Screened Poisson Reconstructioncited by 7
  4. 2024Consistent Point Orientation for Manifold Surfaces via Boundary Integrationcited by 4
  5. 2025MASH: Masked Anchored SpHerical Distances for 3D Shape Representation and Generationcited by 4
  6. 2021Z2P: Instant Visualization of Point Cloudscited by 3
  7. 2025PFF-Net: Patch Feature Fitting for Point Cloud Normal Estimationcited by 3
  8. 2025SDFs from Unoriented Point Clouds using Neural Variational Heat Distancescited by 2
  9. 2025Learning Normals of Noisy Points by Local Gradient-Aware Surface Filteringcited by 2
  10. 2022Unsigned Distance Field as an Accurate 3D Scene Representation for Neural Scene Completioncited by 1
  11. 2022LoopDraw: a Loop-Based Autoregressive Model for Shape Synthesis and Editingcited by 1
  12. 2025A Divide-and-Conquer Approach for Global Orientation of Non-Watertight Scene-Level Point Clouds Using 0-1 Integer Optimizationcited by 1
  13. 2025Self-Supervised Implicit Attention Priors for Point Cloud Reconstructioncited by 1
  14. 2024Refining 3D Point Cloud Normal Estimation via Sample Selectioncited by 0
  15. 2024OCMG-Net: Neural Oriented Normal Refinement for Unstructured Point Cloudscited by 0
  16. 2025Wavelet-based Global Orientation and Surface Reconstruction for Point Cloudscited by 0
  17. 2025Voronoi-Assisted Optimization for Diffusing Unsigned Distance Fields from Unoriented Pointscited by 0
  18. 2026Joint Orientation and Weight Optimization for Robust Watertight Surface Reconstruction via Dirichlet-Regularized Winding Fieldscited by 0
  19. 2026Region of Interest Segmentation and Morphological Analysis for Membranes in Cryo-Electron Tomographycited by 0