mlsanityData to 7 Oct 2026

Learning Inner-Group Relations on Point Clouds

arXiv 2108.12468 ↗First posted 27 Aug 2021cs.CV cs.AI cs.GRcited by 29

Not on the map. Why?

Abstract (arXiv)

The prevalence of relation networks in computer vision is in stark contrast to underexplored point-based methods. In this paper, we explore the possibilities of local relation operators and survey their feasibility. We propose a scalable and efficient module, called group relation aggregator. The module computes a feature of a group based on the aggregation of the features of the inner-group points weighted by geometric relations and semantic relations. We adopt this module to design our RPNet. We further verify the expandability of RPNet, in terms of both depth and width, on the tasks of classification and segmentation. Surprisingly, empirical results show that wider RPNet fits for classification, while deeper RPNet works better on segmentation. RPNet achieves state-of-the-art for classification and segmentation on challenging benchmarks. We also compare our local aggregator with PointNet++, with around 30% parameters and 50% computation saving. Finally, we conduct experiments to reveal the robustness of RPNet with regard to rigid transformation and noises.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 52 of its 65 references that are in the map. First posted on arXiv 27 Aug 2021.

Builds on

52 of 65 references.

References · 52

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  8. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  9. 2017Non-local Neural Networkscited by 2,290
  10. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  11. 2017Deformable Convolutional Networkscited by 1,481
  12. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
38 more
  1. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  2. 2018Self-Attention Generative Adversarial Networkscited by 809
  3. 2018Image Transformercited by 770
  4. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  5. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  6. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  7. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  8. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  9. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  10. 2017Residual Attention Network for Image Classificationcited by 385
  11. 2019Attention Augmented Convolutional Networkscited by 363
  12. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  13. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  14. 2020Exploring Self-attention for Image Recognitioncited by 313
  15. 2017Relation Networks for Object Detectioncited by 305
  16. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  17. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  18. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  19. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  20. 2019Local Relation Networks for Image Recognitioncited by 210
  21. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  22. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  23. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  24. 2020Disentangled Non-Local Neural Networkscited by 132
  25. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  26. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  27. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  28. 2018Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Networkcited by 100
  29. 2018Multiresolution Tree Networks for 3D Point Cloud Processingcited by 91
  30. 2020A Closer Look at Local Aggregation Operators in Point Cloud Analysiscited by 87
  31. 2019SampleNet: Differentiable Point Cloud Samplingcited by 74
  32. 2019Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentationcited by 68
  33. 2018Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Cloudscited by 62
  34. 2020FPConv: Learning Local Flattening for Point Convolutioncited by 55
  35. 2018A Graph-CNN for 3D Point Cloud Classificationcited by 49
  36. 2017O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysiscited by 47
  37. 2019Adaptive Hierarchical Down-Sampling for Point Cloud Classificationcited by 40
  38. 2018Learning Region Features for Object Detectioncited by 15

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 12; 2023: 8; 2024: 5; 2025: 3.

29 papers.

Sort:

  1. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  2. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 262
  3. 2022Surface Representation for Point Cloudscited by 84
  4. 2023Self-positioning Point-based Transformer for Point Cloud Understandingcited by 40
  5. 2022Transformers in 3D Point Clouds: A Surveycited by 31
  6. 2023Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlookcited by 24
  7. 2022FBNet: Feedback Network for Point Cloud Completioncited by 20
  8. 2024Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentationcited by 20
  9. 2023Point Cloud Classification Using Content-based Transformer via Clustering in Feature Spacecited by 19
  10. 2023SE-ORNet: Self-Ensembling Orientation-aware Network for Unsupervised Point Cloud Shape Correspondencecited by 19
  11. 2024Rethinking Few-shot 3D Point Cloud Semantic Segmentationcited by 18
  12. 2024LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernelscited by 15
17 more
  1. 2025Instant4D: 4D Gaussian Splatting in Minutescited by 10
  2. 2024PointGL: A Simple Global-Local Framework for Efficient Point Cloud Analysiscited by 5
  3. 2021CloudWalker: Random walks for 3D point cloud shape analysiscited by 4
  4. 2022PointSCNet: Point Cloud Structure and Correlation Learning Based on Space Filling Curve-Guided Samplingcited by 4
  5. 2022APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Classificationcited by 4
  6. 2022Composite Convolution: a Flexible Operator for Deep Learning on 3D Point Cloudscited by 4
  7. 2022PointNorm: Dual Normalization is All You Need for Point Cloud Analysiscited by 3
  8. 2022PIDS: Joint Point Interaction-Dimension Search for 3D Point Cloudcited by 3
  9. 2023SAT: Size-Aware Transformer for 3D Point Cloud Semantic Segmentationcited by 3
  10. 20243D Object Detection from Point Cloud via Voting Step Diffusioncited by 3
  11. 2023PointCAT: Cross-Attention Transformer for point cloudcited by 2
  12. 2022Point Cloud Recognition with Position-to-Structure Attention Transformerscited by 1
  13. 2023PointeNet: A Lightweight Framework for Effective and Efficient Point Cloud Analysiscited by 1
  14. 20253D Test-time Adaptation via Graph Spectral Driven Point Shiftcited by 1
  15. 2022Adaptive Edge-to-Edge Interaction Learning for Point Cloud Analysiscited by 0
  16. 2023Feature Adversarial Distillation for Point Cloud Classificationcited by 0
  17. 2025BAGNet: A Boundary-Aware Graph Attention Network for 3D Point Cloud Semantic Segmentationcited by 0