Minkowski-MambaNet: A Point Cloud Framework with Selective State Space Models for Forest Biomass Quantification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912640946667520 |
|---|---|
| author | Tu, Jinxiang Ren, Dayong Shi, Fei Jia, Zhenhong Ren, Yahong Qin, Jiwei He, Fang |
| author_facet | Tu, Jinxiang Ren, Dayong Shi, Fei Jia, Zhenhong Ren, Yahong Qin, Jiwei He, Fang |
| contents | Accurate forest biomass quantification is vital for carbon cycle monitoring. While airborne LiDAR excels at capturing 3D forest structure, directly estimating woody volume and Aboveground Biomass (AGB) from point clouds is challenging due to difficulties in modeling long-range dependencies needed to distinguish trees.We propose Minkowski-MambaNet, a novel deep learning framework that directly estimates volume and AGB from raw LiDAR. Its key innovation is integrating the Mamba model's Selective State Space Model (SSM) into a Minkowski network, enabling effective encoding of global context and long-range dependencies for improved tree differentiation. Skip connections are incorporated to enhance features and accelerate convergence.Evaluated on Danish National Forest Inventory LiDAR data, Minkowski-MambaNet significantly outperforms state-of-the-art methods, providing more accurate and robust estimates. Crucially, it requires no Digital Terrain Model (DTM) and is robust to boundary artifacts. This work offers a powerful tool for large-scale forest biomass analysis, advancing LiDAR-based forest inventories. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09367 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Minkowski-MambaNet: A Point Cloud Framework with Selective State Space Models for Forest Biomass Quantification Tu, Jinxiang Ren, Dayong Shi, Fei Jia, Zhenhong Ren, Yahong Qin, Jiwei He, Fang Computer Vision and Pattern Recognition Accurate forest biomass quantification is vital for carbon cycle monitoring. While airborne LiDAR excels at capturing 3D forest structure, directly estimating woody volume and Aboveground Biomass (AGB) from point clouds is challenging due to difficulties in modeling long-range dependencies needed to distinguish trees.We propose Minkowski-MambaNet, a novel deep learning framework that directly estimates volume and AGB from raw LiDAR. Its key innovation is integrating the Mamba model's Selective State Space Model (SSM) into a Minkowski network, enabling effective encoding of global context and long-range dependencies for improved tree differentiation. Skip connections are incorporated to enhance features and accelerate convergence.Evaluated on Danish National Forest Inventory LiDAR data, Minkowski-MambaNet significantly outperforms state-of-the-art methods, providing more accurate and robust estimates. Crucially, it requires no Digital Terrain Model (DTM) and is robust to boundary artifacts. This work offers a powerful tool for large-scale forest biomass analysis, advancing LiDAR-based forest inventories. |
| title | Minkowski-MambaNet: A Point Cloud Framework with Selective State Space Models for Forest Biomass Quantification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.09367 |