mlsanityData to 7 Oct 2026

PointNorm: Dual Normalization is All You Need for Point Cloud Analysis

arXiv 2207.06324 ↗First posted 13 Jul 2022cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Point cloud analysis is challenging due to the irregularity of the point cloud data structure. Existing works typically employ the ad-hoc sampling-grouping operation of PointNet++, followed by sophisticated local and/or global feature extractors for leveraging the 3D geometry of the point cloud. Unfortunately, the sampling-grouping operations do not address the point cloud's irregularity, whereas the intricate local and/or global feature extractors led to poor computational efficiency. In this paper, we introduce a novel DualNorm module after the sampling-grouping operation to effectively and efficiently address the irregularity issue. The DualNorm module consists of Point Normalization, which normalizes the grouped points to the sampled points, and Reverse Point Normalization, which normalizes the sampled points to the grouped points. The proposed framework, PointNorm, utilizes local mean and global standard deviation to benefit from both local and global features while maintaining a faithful inference speed. Experiments show that we achieved excellent accuracy and efficiency on ModelNet40 classification, ScanObjectNN classification, ShapeNetPart Part Segmentation, and S3DIS Semantic Segmentation. Code is available at https://github.com/ShenZheng2000/PointNorm-for-Point-Cloud-Analysis.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 46 of its 62 references that are in the map. First posted on arXiv 13 Jul 2022.

Builds on

46 of 62 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2017Non-local Neural Networkscited by 2,290
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2020Point Transformercited by 1,462
  10. 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,337
  11. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  12. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
34 more
  1. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  2. 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
  3. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  4. 2020PCT: Point cloud transformercited by 730
  5. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  6. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  7. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  8. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  9. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  10. 2018How Does Batch Normalization Help Optimization?cited by 355
  11. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  12. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  13. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  14. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  15. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  16. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  17. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  18. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  19. 2020MVTN: Multi-View Transformation Network for 3D Shape Recognitioncited by 140
  20. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  21. 2022Surface Representation for Point Cloudscited by 84
  22. 2020Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloudcited by 71
  23. 2016SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentationcited by 70
  24. 20203D Point Cloud Processing and Learning for Autonomous Drivingcited by 68
  25. 2021Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancementcited by 60
  26. 2021PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysiscited by 58
  27. 2020Dense-Resolution Network for Point Cloud Classification and Segmentationcited by 45
  28. 2018PVNet: A Joint Convolutional Network of Point Cloud and Multi-View for 3D Shape Recognitioncited by 36
  29. 2020MeshWalker: Deep Mesh Understanding by Random Walkscited by 32
  30. 2020Review: deep learning on 3D point cloudscited by 29
  31. 2021Learning Inner-Group Relations on Point Cloudscited by 29
  32. 2021DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusioncited by 17
  33. 2022Unsupervised Domain Adaptation for Cardiac Segmentation: Towards Structure Mutual Information Maximizationcited by 7
  34. 2022AS-IntroVAE: Adversarial Similarity Distance Makes Robust IntroVAEcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2024Generating CAD Code with Vision-Language Models for 3D Designscited by 61
  2. 2025EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editingcited by 45
  3. 2026HyQuRP: Hybrid quantum-classical neural network with rotational and permutational equivariancecited by 0