# A Graph-CNN for 3D Point Cloud Classification

arXiv: https://arxiv.org/abs/1812.01711 · HTML: https://mlsanity.com/paper/1812.01711/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2018.

## Built on by (most cited first, 30 of 49)

- [Regularization Strategy for Point Cloud via Rigidly Mixed Sample](https://mlsanity.com/paper/2102.01929/) (2021)
- [A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective](https://mlsanity.com/paper/2209.13232/) (2022)
- [Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning](https://mlsanity.com/paper/2107.01886/) (2021)
- [Edge Grasp Network: A Graph-Based SE(3)-invariant Approach to Grasp Detection](https://mlsanity.com/paper/2211.00191/) (2022)
- [Learning Inner-Group Relations on Point Clouds](https://mlsanity.com/paper/2108.12468/) (2021)
- [DRINet++: Efficient Voxel-as-point Point Cloud Segmentation](https://mlsanity.com/paper/2111.08318/) (2021)
- [Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoning](https://mlsanity.com/paper/2202.12588/) (2022)
- [Geometry-Complete Perceptron Networks for 3D Molecular Graphs](https://mlsanity.com/paper/2211.02504/) (2022)
- [PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features](https://mlsanity.com/paper/2102.12093/) (2021)
- [Few-shot Class-incremental Learning for 3D Point Cloud Objects](https://mlsanity.com/paper/2205.15225/) (2022)
- [Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks](https://mlsanity.com/paper/2101.00483/) (2021)
- [SageMix: Saliency-Guided Mixup for Point Clouds](https://mlsanity.com/paper/2210.06944/) (2022)
- [DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds](https://mlsanity.com/paper/2111.08799/) (2021)
- [Training or Architecture? How to Incorporate Invariance in Neural Networks](https://mlsanity.com/paper/2106.10044/) (2021)
- [Point Cloud Upsampling and Normal Estimation using Deep Learning for Robust Surface Reconstruction](https://mlsanity.com/paper/2102.13391/) (2021)
- [PSNet: Fast Data Structuring for Hierarchical Deep Learning on Point Cloud](https://mlsanity.com/paper/2205.14965/) (2022)
- [PointWavelet: Learning in Spectral Domain for 3D Point Cloud Analysis](https://mlsanity.com/paper/2302.05201/) (2023)
- [Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models](https://mlsanity.com/paper/2411.14495/) (2024)
- [No-Reference Point Cloud Quality Assessment via Graph Convolutional Network](https://mlsanity.com/paper/2411.07728/) (2024)
- [Spatio-temporal Graph-RNN for Point Cloud Prediction](https://mlsanity.com/paper/2102.07482/) (2021)
- [Urban GeoBIM construction by integrating semantic LiDAR point clouds with as-designed BIM models](https://mlsanity.com/paper/2304.11719/) (2023)
- [Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations](https://mlsanity.com/paper/2103.00787/) (2021)
- [Point Cloud Audio Processing](https://mlsanity.com/paper/2105.02469/) (2021)
- [Advancements in Point Cloud-Based 3D Defect Detection and Classification for Industrial Systems: A Comprehensive Survey](https://mlsanity.com/paper/2402.12923/) (2024)
- [Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free Adaptor](https://mlsanity.com/paper/2410.09237/) (2024)
- [SN-Graph: a Minimalist 3D Object Representation for Classification](https://mlsanity.com/paper/2105.14784/) (2021)
- [A Simple Strategy to Provable Invariance via Orbit Mapping](https://mlsanity.com/paper/2209.11916/) (2022)
- [PointCAT: Cross-Attention Transformer for point cloud](https://mlsanity.com/paper/2304.03012/) (2023)
- [Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration](https://mlsanity.com/paper/2410.05729/) (2024)
- [MambaTron: Efficient Cross-Modal Point Cloud Enhancement using Aggregate Selective State Space Modeling](https://mlsanity.com/paper/2501.16384/) (2025)

## 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.