# Point Attention Network for Semantic Segmentation of 3D Point Clouds

arXiv: https://arxiv.org/abs/1909.12663 · HTML: https://mlsanity.com/paper/1909.12663/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2019.

## Built on by (most cited first, 29 of 29)

- [Transformers in 3D Point Clouds: A Survey](https://mlsanity.com/paper/2205.07417/) (2022)
- [Deep Learning Based 3D Segmentation: A Survey](https://mlsanity.com/paper/2103.05423/) (2021)
- [PartGlot: Learning Shape Part Segmentation from Language Reference Games](https://mlsanity.com/paper/2112.06390/) (2021)
- [3DCTN: 3D Convolution-Transformer Network for Point Cloud Classification](https://mlsanity.com/paper/2203.00828/) (2022)
- [AttDLNet: Attention-based DL Network for 3D LiDAR Place Recognition](https://mlsanity.com/paper/2106.09637/) (2021)
- [Investigating Attention Mechanism in 3D Point Cloud Object Detection](https://mlsanity.com/paper/2108.00620/) (2021)
- [PnP-3D: A Plug-and-Play for 3D Point Clouds](https://mlsanity.com/paper/2108.07378/) (2021)
- [DLA-Net: Learning Dual Local Attention Features for Semantic Segmentation of Large-Scale Building Facade Point Clouds](https://mlsanity.com/paper/2106.00376/) (2021)
- [Continuous Conditional Random Field Convolution for Point Cloud Segmentation](https://mlsanity.com/paper/2110.06085/) (2021)
- [Full Point Encoding for Local Feature Aggregation in 3D Point Clouds](https://mlsanity.com/paper/2303.04458/) (2023)
- [LATFormer: Locality-Aware Point-View Fusion Transformer for 3D Shape Recognition](https://mlsanity.com/paper/2109.01291/) (2021)
- [Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar Network](https://mlsanity.com/paper/2112.15458/) (2021)
- [PIG-Net: Inception based Deep Learning Architecture for 3D Point Cloud Segmentation](https://mlsanity.com/paper/2101.11987/) (2021)
- [Advancements in Point Cloud-Based 3D Defect Detection and Classification for Industrial Systems: A Comprehensive Survey](https://mlsanity.com/paper/2402.12923/) (2024)
- [Graph Classification via Discriminative Edge Feature Learning](https://mlsanity.com/paper/2210.02060/) (2022)
- [DANet: Density Adaptive Convolutional Network with Interactive Attention for 3D Point Clouds](https://mlsanity.com/paper/2303.04473/) (2023)
- [Graph Structure from Point Clouds: Geometric Attention is All You Need](https://mlsanity.com/paper/2307.16662/) (2023)
- [Rethinking Attention Module Design for Point Cloud Analysis](https://mlsanity.com/paper/2407.19294/) (2024)
- [PointDiffuse: A Dual-Conditional Diffusion Model for Enhanced Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2503.06094/) (2025)
- [Hierarchical Point Cloud Encoding and Decoding with Lightweight Self-Attention based Model](https://mlsanity.com/paper/2202.06407/) (2022)
- [GSTran: Joint Geometric and Semantic Coherence for Point Cloud Segmentation](https://mlsanity.com/paper/2408.11558/) (2024)
- [Dual-Neighborhood Deep Fusion Network for Point Cloud Analysis](https://mlsanity.com/paper/2108.09228/) (2021)
- [3DGTN: 3D Dual-Attention GLocal Transformer Network for Point Cloud Classification and Segmentation](https://mlsanity.com/paper/2209.11255/) (2022)
- [Shrinking unit: a Graph Convolution-Based Unit for CNN-like 3D Point Cloud Feature Extractors](https://mlsanity.com/paper/2209.12770/) (2022)
- [JSMNet Improving Indoor Point Cloud Semantic and Instance Segmentation through Self-Attention and Multiscale](https://mlsanity.com/paper/2309.07425/) (2023)
- [Soft Masked Transformer for Point Cloud Processing with Skip Attention-Based Upsampling](https://mlsanity.com/paper/2403.14124/) (2024)
- [Smart Feature is What You Need](https://mlsanity.com/paper/2406.15805/) (2024)
- [Unlocking Hidden Potential in Point Cloud Networks with Attention-Guided Grouping-Feature Coordination](https://mlsanity.com/paper/2509.16639/) (2025)
- [Channel-Level Relation to Attentive Aggregation with Neighborhood-Homogeneity Constraint for Point Cloud Analysis](https://mlsanity.com/paper/2605.02357/) (2026)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) have performed extremely well on data represented by regularly arranged grids such as images. However, directly leveraging the classic convolution kernels or parameter sharing mechanisms on sparse 3D point clouds is inefficient due to their irregular and unordered nature. We propose a point attention network that learns rich local shape features and their contextual correlations for 3D point cloud semantic segmentation. Since the geometric distribution of the neighboring points is invariant to the point ordering, we propose a Local Attention-Edge Convolution (LAE Conv) to construct a local graph based on the neighborhood points searched in multi-directions. We assign attention coefficients to each edge and then aggregate the point features as a weighted sum of its neighbors. The learned LAE-Conv layer features are then given to a point-wise spatial attention module to generate an interdependency matrix of all points regardless of their distances, which captures long-range spatial contextual features contributing to more precise semantic information. The proposed point attention network consists of an encoder and decoder which, together with the LAE-Conv layers and the point-wise spatial attention modules, make it an end-to-end trainable network for predicting dense labels for 3D point cloud segmentation. Experiments on challenging benchmarks of 3D point clouds show that our algorithm can perform at par or better than the existing state of the art methods.