mlsanityData to 7 Oct 2026

A Graph-CNN for 3D Point Cloud Classification

arXiv 1812.01711 ↗First posted 28 Nov 2018cs.CV cs.LG stat.MLcited by 49

Not on the map. Why?

Abstract (arXiv)

Graph convolutional neural networks (Graph-CNNs) extend traditional CNNs to handle data that is supported on a graph. Major challenges when working with data on graphs are that the support set (the vertices of the graph) do not typically have a natural ordering, and in general, the topology of the graph is not regular (i.e., vertices do not all have the same number of neighbors). Thus, Graph-CNNs have huge potential to deal with 3D point cloud data which has been obtained from sampling a manifold. In this paper, we develop a Graph-CNN for classifying 3D point cloud data, called PointGCN. The architecture combines localized graph convolutions with two types of graph downsampling operations (also known as pooling). By the effective exploration of the point cloud local structure using the Graph-CNN, the proposed architecture achieves competitive performance on the 3D object classification benchmark ModelNet, and our architecture is more stable than competing schemes.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 14; 2023: 8; 2024: 6; 2025: 1; 2026: 1.

49 papers.

Sort:

By area:

  1. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  2. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  3. 2021Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learningcited by 52
  4. 2022Edge Grasp Network: A Graph-Based SE(3)-invariant Approach to Grasp Detectioncited by 34
  5. 2021Learning Inner-Group Relations on Point Cloudscited by 29
  6. 2021DRINet++: Efficient Voxel-as-point Point Cloud Segmentationcited by 23
  7. 2022Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoningcited by 16
  8. 2021PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Featurescited by 15
  9. 2022Geometry-Complete Perceptron Networks for 3D Molecular Graphscited by 15
  10. 2022Few-shot Class-incremental Learning for 3D Point Cloud Objectscited by 13
  11. 2021Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networkscited by 12
  12. 2022SageMix: Saliency-Guided Mixup for Point Cloudscited by 12
37 more
  1. 2021DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Cloudscited by 10
  2. 2021Training or Architecture? How to Incorporate Invariance in Neural Networkscited by 9
  3. 2021Point Cloud Upsampling and Normal Estimation using Deep Learning for Robust Surface Reconstructioncited by 7
  4. 2022PSNet: Fast Data Structuring for Hierarchical Deep Learning on Point Cloudcited by 7
  5. 2023PointWavelet: Learning in Spectral Domain for 3D Point Cloud Analysiscited by 7
  6. 2024Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Modelscited by 7
  7. 2021Spatio-temporal Graph-RNN for Point Cloud Predictioncited by 5
  8. 2024No-Reference Point Cloud Quality Assessment via Graph Convolutional Networkcited by 5
  9. 2023Urban GeoBIM construction by integrating semantic LiDAR point clouds with as-designed BIM modelscited by 4
  10. 2021Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformationscited by 3
  11. 2021Point Cloud Audio Processingcited by 3
  12. 2024Advancements in Point Cloud-Based 3D Defect Detection and Classification for Industrial Systems: A Comprehensive Surveycited by 3
  13. 2024Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free Adaptorcited by 3
  14. 2021SN-Graph: a Minimalist 3D Object Representation for Classificationcited by 2
  15. 2022A Simple Strategy to Provable Invariance via Orbit Mappingcited by 2
  16. 2023PointCAT: Cross-Attention Transformer for point cloudcited by 2
  17. 2024Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registrationcited by 2
  18. 2025MambaTron: Efficient Cross-Modal Point Cloud Enhancement using Aggregate Selective State Space Modelingcited by 2
  19. 2021Uncertainty-Based Dynamic Graph Neighborhoods For Medical Segmentationcited by 1
  20. 2021Structure-Aware Multi-Hop Graph Convolution for Graph Neural Networkscited by 1
  21. 2022PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Treescited by 1
  22. 2023Cloud-RAIN: Point Cloud Analysis with Reflectional Invariancecited by 1
  23. 2023Improving Video Violence Recognition with Human Interaction Learning on 3D Skeleton Point Cloudscited by 1
  24. 2021VA-GCN: A Vector Attention Graph Convolution Network for learning on Point Cloudscited by 0
  25. 2021SINGA-Easy: An Easy-to-Use Framework for MultiModal Analysiscited by 0
  26. 2021VisualTextRank: Unsupervised Graph-based Content Extraction for Automating Ad Text to Image Searchcited by 0
  27. 2021Text is NOT Enough: Integrating Visual Impressions into Open-domain Dialogue Generationcited by 0
  28. 2022Discovering Personalized Semantics for Soft Attributes in Recommender Systems using Concept Activation Vectorscited by 0
  29. 2022Reinforced MOOCs Concept Recommendation in Heterogeneous Information Networkscited by 0
  30. 2022Explanation-Guided Fairness Testing through Genetic Algorithmcited by 0
  31. 2022Using Graph Neural Networks for Program Terminationcited by 0
  32. 2022Learning Latent Part-Whole Hierarchies for Point Cloudscited by 0
  33. 2023Attention-based Graph Convolution Fusing Latent Structures and Multiple Features for Graph Neural Networkscited by 0
  34. 2023Tribe or Not? Critical Inspection of Group Differences Using TribalGramcited by 0
  35. 2023Subspace-Configurable Networkscited by 0
  36. 2024Global Attention-Guided Dual-Domain Point Cloud Feature Learning for Classification and Segmentationcited by 0
  37. 2026Mamba Learns in Context: Structure-Aware Domain Generalization for Multi-Task Point Cloud Understandingcited by 0