# Directionally Constrained Fully Convolutional Neural Network For Airborne Lidar Point Cloud Classification

arXiv: https://arxiv.org/abs/1908.06673 · HTML: https://mlsanity.com/paper/1908.06673/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2019.

## Built on by (most cited first, 6 of 6)

- [Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classification](https://mlsanity.com/paper/2207.10278/) (2022)
- [Unsupervised semantic segmentation of urban high-density multispectral point clouds](https://mlsanity.com/paper/2410.18520/) (2024)
- [HyperPointFormer: Multimodal Fusion in 3D Space with Dual-Branch Cross-Attention Transformers](https://mlsanity.com/paper/2505.23206/) (2025)
- [Learn to Learn Metric Space for Few-Shot Segmentation of 3D Shapes](https://mlsanity.com/paper/2107.02972/) (2021)
- [HAVANA: Hard negAtiVe sAmples aware self-supervised coNtrastive leArning for Airborne laser scanning point clouds semantic segmentation](https://mlsanity.com/paper/2210.10626/) (2022)
- [Twin Deformable Point Convolutions for Point Cloud Semantic Segmentation in Remote Sensing Scenes](https://mlsanity.com/paper/2405.19735/) (2024)

## Abstract (arXiv)

Point cloud classification plays an important role in a wide range of airborne light detection and ranging (LiDAR) applications, such as topographic mapping, forest monitoring, power line detection, and road detection. However, due to the sensor noise, high redundancy, incompleteness, and complexity of airborne LiDAR systems, point cloud classification is challenging. In this paper, we proposed a directionally constrained fully convolutional neural network (D-FCN) that can take the original 3D coordinates and LiDAR intensity as input; thus, it can directly apply to unstructured 3D point clouds for semantic labeling. Specifically, we first introduce a novel directionally constrained point convolution (D-Conv) module to extract locally representative features of 3D point sets from the projected 2D receptive fields. To make full use of the orientation information of neighborhood points, the proposed D-Conv module performs convolution in an orientation-aware manner by using a directionally constrained nearest neighborhood search. Then, we designed a multiscale fully convolutional neural network with downsampling and upsampling blocks to enable multiscale point feature learning. The proposed D-FCN model can therefore process input point cloud with arbitrary sizes and directly predict the semantic labels for all the input points in an end-to-end manner. Without involving additional geometry features as input, the proposed method has demonstrated superior performance on the International Society for Photogrammetry and Remote Sensing (ISPRS) 3D labeling benchmark dataset. The results show that our model has achieved a new state-of-the-art level of performance with an average F1 score of 70.7%, and it has improved the performance by a large margin on categories with a small number of points (such as powerline, car, and facade).