mlsanityData to 7 Oct 2026

Automated forest inventory: analysis of high-density airborne LiDAR point clouds with 3D deep learning

arXiv 2312.15084 ↗First posted 22 Dec 2023cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Detailed forest inventories are critical for sustainable and flexible management of forest resources, to conserve various ecosystem services. Modern airborne laser scanners deliver high-density point clouds with great potential for fine-scale forest inventory and analysis, but automatically partitioning those point clouds into meaningful entities like individual trees or tree components remains a challenge. The present study aims to fill this gap and introduces a deep learning framework, termed ForAINet, that is able to perform such a segmentation across diverse forest types and geographic regions. From the segmented data, we then derive relevant biophysical parameters of individual trees as well as stands. The system has been tested on FOR-Instance, a dataset of point clouds that have been acquired in five different countries using surveying drones. The segmentation back-end achieves over 85% F-score for individual trees, respectively over 73% mean IoU across five semantic categories: ground, low vegetation, stems, live branches and dead branches. Building on the segmentation results our pipeline then densely calculates biophysical features of each individual tree (height, crown diameter, crown volume, DBH, and location) and properties per stand (digital terrain model and stand density). Especially crown-related features are in most cases retrieved with high accuracy, whereas the estimates for DBH and location are less reliable, due to the airborne scanning setup.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 19 of its 90 references that are in the map. First posted on arXiv 22 Dec 2023.

Builds on

19 of 90 references.

References · 19

  1. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  2. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  3. 2020PointGroup: Dual-Set Point Grouping for 3D Instance Segmentationcited by 318
  4. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 197
  5. 20203D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentationcited by 140
  6. 2021Hierarchical Aggregation for 3D Instance Segmentationcited by 126
  7. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  8. 2019Associatively Segmenting Instances and Semantics in Point Cloudscited by 86
  9. 20193D Instance Segmentation via Multi-Task Metric Learningcited by 79
  10. 2022CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentationcited by 54
  11. 2021A Survey on Deep Domain Adaptation for LiDAR Perceptioncited by 46
  12. 2022MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentationcited by 29
7 more
  1. 2020Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentationcited by 26
  2. 2020Torch-Points3D: A Modular Multi-Task Frameworkfor Reproducible Deep Learning on 3D Point Cloudscited by 23
  3. 2023Point2Tree(P2T) -- framework for parameter tuning of semantic and instance segmentation used with mobile laser scanning data in coniferous forestcited by 14
  4. 2021A Technical Survey and Evaluation of Traditional Point Cloud Clustering Methods for LiDAR Panoptic Segmentationcited by 9
  5. 2023A Review of Panoptic Segmentation for Mobile Mapping Point Cloudscited by 8
  6. 2023Towards accurate instance segmentation in large-scale LiDAR point cloudscited by 8
  7. 2017Forest understory trees can be segmented accurately within sufficiently dense airborne laser scanning point cloudscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 13; 2026: 8.

23 papers.

Sort:

By area:

  1. 2024SegmentAnyTree: A sensor and platform agnostic deep learning model for tree segmentation using laser scanning datacited by 16
  2. 2024Benchmarking tree species classification from proximally-sensed laser scanning data: introducing the FOR-species20K datasetcited by 12
  3. 2025ForestFormer3D: A Unified Framework for End-to-End Segmentation of Forest LiDAR 3D Point Cloudscited by 12
  4. 2025Unsupervised deep learning for semantic segmentation of multispectral LiDAR forest point cloudscited by 7
  5. 2025Multispectral airborne laser scanning for tree species classification: a benchmark of machine learning and deep learning algorithmscited by 6
  6. 2025Bringing SAM to new heights: Leveraging elevation data for tree crown segmentation from drone imagerycited by 6
  7. 2025Scaling Up Forest Vision with Synthetic Datacited by 3
  8. 2026ForestMamba: Sparse Mamba with Geometry-guided Queries for 3D Forest Point Cloud Segmentationcited by 3
  9. 2025Manual Labelling Artificially Inflates Deep Learning-Based Segmentation Performance on RGB Images of Closed Canopy: Validation Using TLScited by 2
  10. 20253D forest semantic segmentation using multispectral LiDAR and 3D deep learningcited by 2
  11. 2025Benchmarking individual tree segmentation using multispectral airborne laser scanning data: the FGI-EMIT datasetcited by 2
  12. 2025Towards scalable organ level 3D plant segmentation: Bridging the data algorithm computing gapcited by 1
11 more
  1. 2025WHU-STree: A Multi-modal Benchmark Dataset for Street Tree Inventorycited by 1
  2. 2025treeX: Unsupervised Tree Instance Segmentation in Dense Forest Point Cloudscited by 0
  3. 2025Minkowski-MambaNet: A Point Cloud Framework with Selective State Space Models for Forest Biomass Quantificationcited by 0
  4. 2025NormalView: tree species classification from backpack and aerial lidar data using geometric projectionscited by 0
  5. 2026LeafInst - Unified Instance Segmentation Network for Fine-Grained Forestry Leaf Phenotype Analysis: A New UAV based Benchmarkcited by 0
  6. 2026In-Field 3D Wheat Head Instance Segmentation From TLS Point Clouds Using Deep Learning Without Manual Labelscited by 0
  7. 2026SparseGF: A Height-Aware Sparse Segmentation Framework with Context Compression for Robust Ground Filtering Across Urban to Natural Scenescited by 0
  8. 2026SelectAnyTree: A Promptable Instance Segmentation Model for 3D Forest LiDAR Point Cloudscited by 0
  9. 2026A Framework for Individual Tree Growth Reconstruction Using Multi-Platform Laser Scanningcited by 0
  10. 2026CedarCypress3D: an annotated UAV-LiDAR dataset of individual trees in planted cedar and cypress forestscited by 0
  11. 2026Toward a foundation model for forest point cloudscited by 0