# GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud

arXiv: https://arxiv.org/abs/1905.08705 · HTML: https://mlsanity.com/paper/1905.08705/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2019.

## Built on by (most cited first, 15 of 15)

- [Particle Transformer for Jet Tagging](https://mlsanity.com/paper/2202.03772/) (2022)
- [A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective](https://mlsanity.com/paper/2209.13232/) (2022)
- [Attention-based Point Cloud Edge Sampling](https://mlsanity.com/paper/2302.14673/) (2023)
- [3DCTN: 3D Convolution-Transformer Network for Point Cloud Classification](https://mlsanity.com/paper/2203.00828/) (2022)
- [Point Cloud Transformers applied to Collider Physics](https://mlsanity.com/paper/2102.05073/) (2021)
- [Sim2real Transfer Learning for Point Cloud Segmentation: An Industrial Application Case on Autonomous Disassembly](https://mlsanity.com/paper/2301.05033/) (2023)
- [ARM3D: Attention-based relation module for indoor 3D object detection](https://mlsanity.com/paper/2202.09715/) (2022)
- [PnP-3D: A Plug-and-Play for 3D Point Clouds](https://mlsanity.com/paper/2108.07378/) (2021)
- [GAM : Gradient Attention Module of Optimization for Point Clouds Analysis](https://mlsanity.com/paper/2303.10543/) (2023)
- [Height Estimation of Children under Five Years using Depth Images](https://mlsanity.com/paper/2105.01688/) (2021)
- [SynMotor: A Benchmark Suite for Object Attribute Regression and Multi-task Learning](https://mlsanity.com/paper/2301.05027/) (2023)
- [ANTLER: Bayesian Nonlinear Tensor Learning and Modeler for Unstructured, Varying-Size Point Cloud Data](https://mlsanity.com/paper/2202.13788/) (2022)
- [Shrinking unit: a Graph Convolution-Based Unit for CNN-like 3D Point Cloud Feature Extractors](https://mlsanity.com/paper/2209.12770/) (2022)
- [MLGCN: An Ultra Efficient Graph Convolution Neural Model For 3D Point Cloud Analysis](https://mlsanity.com/paper/2303.17748/) (2023)
- [Global Attention-Guided Dual-Domain Point Cloud Feature Learning for Classification and Segmentation](https://mlsanity.com/paper/2407.08994/) (2024)

## Abstract (arXiv)

Exploiting fine-grained semantic features on point cloud is still challenging due to its irregular and sparse structure in a non-Euclidean space. Among existing studies, PointNet provides an efficient and promising approach to learn shape features directly on unordered 3D point cloud and has achieved competitive performance. However, local feature that is helpful towards better contextual learning is not considered. Meanwhile, attention mechanism shows efficiency in capturing node representation on graph-based data by attending over neighboring nodes. In this paper, we propose a novel neural network for point cloud, dubbed GAPNet, to learn local geometric representations by embedding graph attention mechanism within stacked Multi-Layer-Perceptron (MLP) layers. Firstly, we introduce a GAPLayer to learn attention features for each point by highlighting different attention weights on neighborhood. Secondly, in order to exploit sufficient features, a multi-head mechanism is employed to allow GAPLayer to aggregate different features from independent heads. Thirdly, we propose an attention pooling layer over neighbors to capture local signature aimed at enhancing network robustness. Finally, GAPNet applies stacked MLP layers to attention features and local signature to fully extract local geometric structures. The proposed GAPNet architecture is tested on the ModelNet40 and ShapeNet part datasets, and achieves state-of-the-art performance in both shape classification and part segmentation tasks.