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

• URL: http://arxiv.org/abs/2506.16991v2
• Date: Fri, 01 Aug 2025 05:36:38 GMT
• Title: ForestFormer3D: A Unified Framework for End-to-End Segmentation of Forest LiDAR 3D Point Clouds
• Authors: Binbin Xiang, Maciej Wielgosz, Stefano Puliti, Kamil Král, Martin Krůček, Azim Missarov, Rasmus Astrup,
• Abstract summary: We present ForestFormer3D, a new unified and end-to-end framework for precise individual tree and semantic segmentation.<n>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.<n>Our model achieves state-of-the-art performance for individual tree segmentation on the newly introduced FOR-instanceV2 dataset.
• Score: 0.06282171844772422
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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/.

Related papers

• Not Every Tree Is a Forest: Benchmarking Forest Types from Satellite Remote Sensing [1.2266381182650026]
  This work introduces ForTy, a benchmark for global-scale FORest TYpes mapping using multi-temporal satellite data.<n>The benchmark comprises 200,000 time series of image patches, each consisting of Sentinel-2, Sentinel-1, climate, and elevation data.<n>We evaluate the forest types dataset using several baseline models, including convolution neural networks and transformer-based models.
  arXiv  Detail & Related papers  (2025-05-03T12:20:50Z)
• PointsToWood: A deep learning framework for complete canopy leaf-wood segmentation of TLS data across diverse European forests [0.0]
  We show a new framework that uses a deep learning architecture newly developed from PointNet and point clouds for processing 3D point clouds.<n>We evaluate its performance across open datasets from boreal, temperate, Mediterranean and tropical regions.<n>Results show consistent outperformance against the most widely used PointNet based approach for leaf/wood segmentation.
  arXiv  Detail & Related papers  (2025-03-06T13:23:03Z)
• SegmentAnyTree: A sensor and platform agnostic deep learning model for tree segmentation using laser scanning data [15.438892555484616]
  This research advances individual tree crown (ITC) segmentation in lidar data, using a deep learning model applicable to various laser scanning types. It addresses the challenge of transferability across different data characteristics in 3D forest scene analysis. The model, based on PointGroup architecture, is a 3D CNN with separate heads for semantic and instance segmentation.
  arXiv  Detail & Related papers  (2024-01-28T19:47:17Z)
• SAI3D: Segment Any Instance in 3D Scenes [68.57002591841034]
  We introduce SAI3D, a novel zero-shot 3D instance segmentation approach. Our method partitions a 3D scene into geometric primitives, which are then progressively merged into 3D instance segmentations. Empirical evaluations on ScanNet, Matterport3D and the more challenging ScanNet++ datasets demonstrate the superiority of our approach.
  arXiv  Detail & Related papers  (2023-12-17T09:05:47Z)
• Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentation [67.07112533415116]
  We present a novel framework that adapts various foundational models for the 3D point cloud segmentation task. Our approach involves making initial predictions of 2D semantic masks using different large vision models. To generate robust 3D semantic pseudo labels, we introduce a semantic label fusion strategy that effectively combines all the results via voting.
  arXiv  Detail & Related papers  (2023-11-03T15:41:15Z)
• FOR-instance: a UAV laser scanning benchmark dataset for semantic and instance segmentation of individual trees [0.06597195879147556]
  FOR-instance dataset comprises five curated and ML-ready UAV-based laser scanning data collections. The dataset is divided into development and test subsets, enabling method advancement and evaluation. The inclusion of diameter at breast height data expands its utility to the measurement of a classic tree variable.
  arXiv  Detail & Related papers  (2023-09-03T22:08:29Z)
• ForensicsForest Family: A Series of Multi-scale Hierarchical Cascade Forests for Detecting GAN-generated Faces [53.739014757621376]
  We describe a simple and effective forest-based method set called em ForensicsForest Family to detect GAN-generate faces. ForenscisForest is a newly proposed Multi-scale Hierarchical Cascade Forest. Hybrid ForensicsForest integrates the CNN layers into models. Divide-and-Conquer ForensicsForest can construct a forest model using only a portion of training samplings.
  arXiv  Detail & Related papers  (2023-08-02T06:41:19Z)
• Point2Tree(P2T) -- framework for parameter tuning of semantic and instance segmentation used with mobile laser scanning data in coniferous forest [0.22940141855172028]
  We train a model based on Pointnet++ architecture which achieves 0.92 F1-score in semantic segmentation. As a second step in our pipeline we used graph-based approach for instance segmentation which reached F1-score approx. 0.6.
  arXiv  Detail & Related papers  (2023-05-04T08:45:17Z)
• FinnWoodlands Dataset [12.386304516106852]
  textitFinns comprises a total of 4226 objects manually annotated, out of which 2562 objects correspond to tree trunks. Our dataset can be used in forestry applications where a holistic representation of the environment is relevant.
  arXiv  Detail & Related papers  (2023-04-03T08:28:13Z)
• Multi-Layer Modeling of Dense Vegetation from Aerial LiDAR Scans [4.129847064263057]
  We release WildForest3D, which consists of 29 study plots and over 2000 individual trees across 47 000m2 with dense 3D annotation. We propose a 3D deep network architecture predicting for the first time both 3D point-wise labels and high-resolution occupancy meshes simultaneously.
  arXiv  Detail & Related papers  (2022-04-25T12:47:05Z)
• Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception [122.53774221136193]
  State-of-the-art methods for driving-scene LiDAR-based perception often project the point clouds to 2D space and then process them via 2D convolution. A natural remedy is to utilize the 3D voxelization and 3D convolution network. We propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern.
  arXiv  Detail & Related papers  (2021-09-12T06:25:11Z)
• Making CNNs Interpretable by Building Dynamic Sequential Decision Forests with Top-down Hierarchy Learning [62.82046926149371]
  We propose a generic model transfer scheme to make Convlutional Neural Networks (CNNs) interpretable. We achieve this by building a differentiable decision forest on top of CNNs. We name the transferred model deep Dynamic Sequential Decision Forest (dDSDF)
  arXiv  Detail & Related papers  (2021-06-05T07:41:18Z)
• Growing Deep Forests Efficiently with Soft Routing and Learned Connectivity [79.83903179393164]
  This paper further extends the deep forest idea in several important aspects. We employ a probabilistic tree whose nodes make probabilistic routing decisions, a.k.a., soft routing, rather than hard binary decisions. Experiments on the MNIST dataset demonstrate that our empowered deep forests can achieve better or comparable performance than [1],[3].
  arXiv  Detail & Related papers  (2020-12-29T18:05:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.