mlsanityData to 14 Oct 2026

ForestFormer3D: A Unified Framework for End-to-End Segmentation of Forest LiDAR 3D Point Clouds

arXiv 2506.16991 ↗First posted 20 Jun 2025cs.CV cs.AIcited by 13

Not on the map. Why?

Abstract (arXiv)

The segmentation of forest LiDAR 3D point clouds, including both individual tree and semantic segmentation, is fundamental for advancing forest management and ecological research. However, current approaches often struggle with the complexity and variability of natural forest environments. We present ForestFormer3D, a new unified and end-to-end framework designed for precise individual tree and semantic segmentation. ForestFormer3D incorporates ISA-guided query point selection, a score-based block merging strategy during inference, and a one-to-many association mechanism for effective training. By combining these new components, our model achieves state-of-the-art performance for individual tree segmentation on the newly introduced FOR-instanceV2 dataset, which spans diverse forest types and regions. Additionally, ForestFormer3D generalizes well to unseen test sets (Wytham woods and LAUTx), showcasing its robustness across different forest conditions and sensor modalities. The FOR-instanceV2 dataset and the ForestFormer3D code are publicly available at https://bxiang233.github.io/FF3D/.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 38 of its 74 references that are in the map. First posted on arXiv 20 Jun 2025.

Builds on

38 of 74 references.

References · 38

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  5. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  6. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  7. 2021Conditional DETR for Fast Training Convergencecited by 424
  8. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 406
  9. 2020PointGroup: Dual-Set Point Grouping for 3D Instance Segmentationcited by 321
  10. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 303
  11. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 274
  12. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 200
26 more
  1. 2020OccuSeg: Occupancy-aware 3D Instance Segmentationcited by 177
  2. 2017SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentationcited by 169
  3. 2019Learning Object Bounding Boxes for 3D Instance Segmentation on Point Cloudscited by 156
  4. 2018GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloudcited by 146
  5. 20203D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentationcited by 141
  6. 2021Hierarchical Aggregation for 3D Instance Segmentationcited by 127
  7. 2022Superpoint Transformer for 3D Scene Instance Segmentationcited by 116
  8. 2023OneFormer3D: One Transformer for Unified Point Cloud Segmentationcited by 95
  9. 2019Associatively Segmenting Instances and Semantics in Point Cloudscited by 86
  10. 2019JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with Multi-Task Pointwise Networks and Multi-Value Conditional Random Fieldscited by 62
  11. 2023FastInst: A Simple Query-Based Model for Real-Time Instance Segmentationcited by 32
  12. 2023Top-Down Beats Bottom-Up in 3D Instance Segmentationcited by 31
  13. 2022MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentationcited by 30
  14. 2019MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentationcited by 25
  15. 2023Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representationcited by 24
  16. 2023Automated forest inventory: analysis of high-density airborne LiDAR point clouds with 3D deep learningcited by 23
  17. 2023FOR-instance: a UAV laser scanning benchmark dataset for semantic and instance segmentation of individual treescited by 21
  18. 20193D-BEVIS: Bird's-Eye-View Instance Segmentationcited by 17
  19. 2024SegmentAnyTree: A sensor and platform agnostic deep learning model for tree segmentation using laser scanning datacited by 17
  20. 20223D-QueryIS: A Query-based Framework for 3D Instance Segmentationcited by 14
  21. 2023Point2Tree(P2T) -- framework for parameter tuning of semantic and instance segmentation used with mobile laser scanning data in coniferous forestcited by 14
  22. 2024SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentationcited by 12
  23. 2023Towards accurate instance segmentation in large-scale LiDAR point cloudscited by 8
  24. 2023Semantic segmentation of sparse irregular point clouds for leaf/wood discriminationcited by 6
  25. 2023Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scanscited by 5
  26. 2024Improved Block Merging for 3D Point Cloud Instance Segmentationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 9.

13 papers.

Sort:

By area:

  1. 2026SelvaMask: Segmenting Trees in Tropical Forests and Beyondcited by 5
  2. 2026ForestMamba: Sparse Mamba with Geometry-guided Queries for 3D Forest Point Cloud Segmentationcited by 4
  3. 2025Scaling Up Forest Vision with Synthetic Datacited by 3
  4. 2025Benchmarking individual tree segmentation using multispectral airborne laser scanning data: the FGI-EMIT datasetcited by 2
  5. 2025treeX: Unsupervised Tree Instance Segmentation in Dense Forest Point Cloudscited by 0
  6. 2025NormalView: tree species classification from backpack and aerial lidar data using geometric projectionscited by 0
  7. 2026TreeDGS: Aerial Gaussian Splatting for Distant DBH Measurementcited by 0
  8. 2026FSKD: Monocular Forest Structure Inference via LiDAR-to-RGBI Knowledge Distillationcited 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. 2026The Role of Radiometric Features in Cross-Site Leaf-Wood Segmentation of LiDAR Point Cloudscited by 0
  12. 2026Toward a foundation model for forest point cloudscited by 0
1 more
  1. 2026ForestQuery: Boundary-Aware and Spatially Anchored Query Learning for Unified Forest Point Cloud Segmentationcited by 0