mlsanityData to 7 Oct 2026

Unsupervised semantic segmentation of urban high-density multispectral point clouds

arXiv 2410.18520 ↗First posted 24 Oct 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

The availability of highly accurate urban airborne laser scanning (ALS) data will increase rapidly in the future, especially as acquisition costs decrease, for example through the use of drones. Current challenges in data processing are related to the limited spectral information and low point density of most ALS datasets. Another challenge will be the growing need for annotated training data, frequently produced by manual processes, to enable semantic interpretation of point clouds. This study proposes to semantically segment new high-density (1200 points per square metre on average) multispectral ALS data with an unsupervised ground-aware deep clustering method GroupSP inspired by the unsupervised GrowSP algorithm. GroupSP divides the scene into superpoints as a preprocessing step. The neural network is trained iteratively by grouping the superpoints and using the grouping assignments as pseudo-labels. The predictions for the unseen data are given by over-segmenting the test set and mapping the predicted classes into ground truth classes manually or with automated majority voting. GroupSP obtained an overall accuracy (oAcc) of 97% and a mean intersection over union (mIoU) of 80%. When compared to other unsupervised semantic segmentation methods, GroupSP outperformed GrowSP and non-deep K-means. However, a supervised random forest classifier outperformed GroupSP. The labelling efforts in GroupSP can be minimal; it was shown, that the GroupSP can semantically segment seven urban classes (building, high vegetation, low vegetation, asphalt, rock, football field, and gravel) with oAcc of 95% and mIoU of 75% using only 0.004% of the available annotated points in the mapping assignment. Finally, the multispectral information was examined; adding each new spectral channel improved the mIoU. Additionally, echo deviation was valuable, especially when distinguishing ground-level classes.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 18 of its 91 references that are in the map. First posted on arXiv 24 Oct 2024.

Builds on

18 of 91 references.

References · 18

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  6. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  7. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  8. 2023Efficient 3D Semantic Segmentation with Superpoint Transformercited by 56
  9. 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
  10. 2023GrowSP: Unsupervised Semantic Segmentation of 3D Point Cloudscited by 34
  11. 2022OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Cloudscited by 24
  12. 2023U3DS3: Unsupervised 3D Semantic Scene Segmentationcited by 16
6 more
  1. 2023PointDC:Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-modal Distillation and Super-Voxel Clusteringcited by 15
  2. 2021A new weakly supervised approach for ALS point cloud semantic segmentationcited by 12
  3. 2019Directionally Constrained Fully Convolutional Neural Network For Airborne Lidar Point Cloud Classificationcited by 6
  4. 2023Deep Unsupervised Learning for 3D ALS Point Cloud Change Detectioncited by 5
  5. 2023DC3DCD: unsupervised learning for multiclass 3D point cloud change detectioncited by 3
  6. 2023Self-Supervised Pre-Training Boosts Semantic Scene Segmentation on LiDAR Datacited by 2

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Cloudscited by 8
  2. 2025Unsupervised deep learning for semantic segmentation of multispectral LiDAR forest point cloudscited by 7
  3. 2025Multispectral airborne laser scanning for tree species classification: a benchmark of machine learning and deep learning algorithmscited by 6
  4. 2025Benchmarking individual tree segmentation using multispectral airborne laser scanning data: the FGI-EMIT datasetcited by 2