用新型模型直接从激光点云估算森林生物量，精度更高且无需地形数据。
Minkowski-MambaNet: A Point Cloud Framework with Selective State Space Models for Forest Biomass Quantification
- 将选择性状态空间模型融入点云网络，捕捉远距离树木依赖关系。
- 在丹麦森林普查数据上优于现有方法，体积与生物量估计更准确。
- 无需数字地形模型，抗边界伪影，适合大范围森林监测应用。
精准的森林生物量量化对碳循环监测至关重要。尽管机载激光雷达（LiDAR）能有效捕捉三维森林结构，但直接从点云估计木质体积和地上生物量（AGB）仍具挑战，主要因难以建模长程依赖以区分树木。本文提出Minkowski-MambaNet，一种新颖的深度学习框架，可直接从原始LiDAR点云估计体积与AGB。其核心创新在于将Mamba模型的选择性状态空间模型（SSM）集成至Minkowski网络中，有效编码全局上下文与长程依赖，提升树木区分能力。引入跳跃连接以增强特征表示并加速收敛。在丹麦国家森林清查LiDAR数据上评估，Minkowski-MambaNet显著优于当前最优方法，提供更精确、鲁棒的估计结果。关键优势在于无需数字地形模型（DTM），且对边界伪影具有强鲁棒性。该工作为大规模森林生物量分析提供了强大工具，推动基于LiDAR的森林清查发展。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。