# ForestMamba: Sparse Mamba with Geometry-guided Queries for 3D Forest Point Cloud Segmentation

arXiv: https://arxiv.org/abs/2606.01549 · HTML: https://mlsanity.com/paper/2606.01549/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Point clouds, detection and remote sensing, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 23 of its 43 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Placed in

- State-space sequence models (S4, Mamba) / [Point clouds, detection and remote sensing](https://mlsanity.com/ssm/point-clouds-detection-and-remote-sensing/)

## Builds on (most cited first, 23 of 23)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [PointMamba: A Simple State Space Model for Point Cloud Analysis](https://mlsanity.com/paper/2402.10739/) (2024)
- [OneFormer3D: One Transformer for Unified Point Cloud Segmentation](https://mlsanity.com/paper/2311.14405/) (2023)
- [Point Cloud Mamba: Point Cloud Learning via State Space Model](https://mlsanity.com/paper/2403.00762/) (2024)
- [Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model](https://mlsanity.com/paper/2404.14966/) (2024)
- [Automated forest inventory: analysis of high-density airborne LiDAR point clouds with 3D deep learning](https://mlsanity.com/paper/2312.15084/) (2023)
- [TreeLearn: A deep learning method for segmenting individual trees from ground-based LiDAR forest point clouds](https://mlsanity.com/paper/2309.08471/) (2023)
- [ForestFormer3D: A Unified Framework for End-to-End Segmentation of Forest LiDAR 3D Point Clouds](https://mlsanity.com/paper/2506.16991/) (2025)
- [Test-Time Augmentation for 3D Point Cloud Classification and Segmentation](https://mlsanity.com/paper/2311.13152/) (2023)
- [LaSSM: Efficient Semantic-Spatial Query Decoding via Local Aggregation and State Space Models for 3D Instance Segmentation](https://mlsanity.com/paper/2602.11007/) (2026)
- [Towards general deep-learning-based tree instance segmentation models](https://mlsanity.com/paper/2405.02061/) (2024)

## Built on by (most cited first, 4 of 4)

- [SegmentAnyTreeV2: Scaling Transformer-Based Tree Instance Segmentation Across Sensors, Platforms, and Forests](https://mlsanity.com/paper/2606.08206/) (2026)
- [SelectAnyTree: A Promptable Instance Segmentation Model for 3D Forest LiDAR Point Clouds](https://mlsanity.com/paper/2606.27491/) (2026)
- [Toward a foundation model for forest point clouds](https://mlsanity.com/paper/2609.24787/) (2026)
- [ForestQuery: Boundary-Aware and Spatially Anchored Query Learning for Unified Forest Point Cloud Segmentation](https://mlsanity.com/paper/2610.03403/) (2026)

## Abstract (arXiv)

Semantic and instance segmentation of terrestrial and drone LiDAR point clouds is emerging as a transformative approach for converting the complex 3D structure of forests into actionable information for forest monitoring and biodiversity assessment. However, forest LiDAR scenes remain highly challenging due to their large data volumes, irregular sampling density, overlapping and complex canopy structure, and geographic variability. Existing methods based on sparse convolutions or Transformers achieve promising results, but suffer from two key limitations: Quadratic complexity of attention scales poorly to large forest scenes, and generic context modeling does not exploit forest structural priors, limiting tree separation in complex regions. To address these challenges, we propose ForestMamba, which integrates forest-specific priors with linear-time state-space modeling for efficient, structure-aware learning. First, we introduce a sparse encoder with vertical-priority slab serialization that organizes sparse voxels into vertically coherent sequences for efficient long-range context modeling. Second, we propose a geometry-guided query initialization strategy based on an on-the-fly multi-scale Canopy Height Model, where canopy maxima provide ecologically meaningful query seeds, supplemented by Farthest Point Sampling to cover understory trees. Third, we design a Mamba-based query decoder that combines local kNN voxel aggregation with a spatial dual-path Mamba for query refinement with linear computational complexity. Extensive experiments across seven forest regions demonstrate that ForestMamba consistently outperforms existing baselines in both segmentation tasks, while achieving 3 times faster inference and 2.3 times lower GPU memory than Transformer-based methods. The source code is available at https://github.com/thanhhff/ForestMamba.