mlsanityData to 7 Oct 2026

PSNet: Fast Data Structuring for Hierarchical Deep Learning on Point Cloud

arXiv 2205.14965 ↗First posted 30 May 2022cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

In order to retain more feature information of local areas on a point cloud, local grouping and subsampling are the necessary data structuring steps in most hierarchical deep learning models. Due to the disorder nature of the points in a point cloud, the significant time cost may be consumed when grouping and subsampling the points, which consequently results in poor scalability. This paper proposes a fast data structuring method called PSNet (Point Structuring Net). PSNet transforms the spatial features of the points and matches them to the features of local areas in a point cloud. PSNet achieves grouping and sampling at the same time while the existing methods process sampling and grouping in two separate steps (such as using FPS plus kNN). PSNet performs feature transformation pointwise while the existing methods uses the spatial relationship among the points as the reference for grouping. Thanks to these features, PSNet has two important advantages: 1) the grouping and sampling results obtained by PSNet is stable and permutation invariant; and 2) PSNet can be easily parallelized. PSNet can replace the data structuring methods in the mainstream point cloud deep learning models in a plug-and-play manner. We have conducted extensive experiments. The results show that PSNet can improve the training and inference speed significantly while maintaining the model accuracy.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 36 of its 63 references that are in the map. First posted on arXiv 30 May 2022.

Builds on

36 of 63 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2014Going Deeper with Convolutionscited by 4,231
  8. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  9. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  10. 2017Deformable Convolutional Networkscited by 1,481
  11. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  12. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
24 more
  1. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  2. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  3. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  4. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  5. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  6. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  7. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  8. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  9. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  10. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  11. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  12. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  13. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  14. 2016Generative and Discriminative Voxel Modeling with Convolutional Neural Networkscited by 128
  15. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  16. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  17. 2019Concrete Autoencoders for Differentiable Feature Selection and Reconstructioncited by 90
  18. 2019Interpolated Convolutional Networks for 3D Point Cloud Understandingcited by 86
  19. 2019SampleNet: Differentiable Point Cloud Samplingcited by 74
  20. 2019A-CNN: Annularly Convolutional Neural Networks on Point Cloudscited by 66
  21. 2018A Graph-CNN for 3D Point Cloud Classificationcited by 49
  22. 2017O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysiscited by 47
  23. 2019Adaptive Hierarchical Down-Sampling for Point Cloud Classificationcited by 40
  24. 2021From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detectioncited by 24

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 4; 2024: 0; 2025: 1.

7 papers.

  1. 2022LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformerscited by 21
  2. 2022Boosting Point-BERT by Multi-choice Tokenscited by 5
  3. 2023GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentationcited by 3
  4. 2023Local region-learning modules for point cloud classificationcited by 1
  5. 2023Hierarchical Adaptive Voxel-guided Sampling for Real-time Applications in Large-scale Point Cloudscited by 1
  6. 2023VTPNet for 3D deep learning on point cloudcited by 0
  7. 2025RefComp: A Reference-guided Unified Framework for Unpaired Point Cloud Completioncited by 0