针对点云密度差异大的树木分类问题，提出分尺度动态图卷积网络。
MS-DGCNN++: Multi-Scale Dynamic Graph Convolution with Scale-Dependent Normalization for Robust LiDAR Tree Species Classification
- 按局部与中程尺度采用不同边特征编码方式
- 在真实数据集上达92.91%准确率，优于多数模型
- 对稀疏点云和噪声有强鲁棒性，适合野外部署
基于图的深度学习在激光雷达点云中通过边特征编码几何信息，但传统方法在各尺度使用相同编码，尤其在树干与树冠点密度相差数个数量级的树木分类任务中表现受限。我们证明此设计次优：归一化方向特征的均方误差随点间距离s呈1/s²衰减，而原始位移误差恒定，表明不同编码适用于不同信噪比（SNR）场景。为此提出MS-DGCNN++，一种多尺度动态图卷积网络，采用尺度依赖的边编码：局部尺度用原始向量（低SNR），中程尺度用原始+归一化向量（高SNR）。五组消融实验验证：编码方式提升整体准确率4–6%；密度随机丢弃下退化最平缓；噪声测试显示理论转换点位于SNR₂≈1.22；最大池化溯源发现原始编码下远邻胜出85%竞争，归一化有效消除该偏差；各向同性分析显示归一化使有效秩几乎翻倍。在STPCTLS数据集（7类，地面激光扫描）上，以仅1.81M参数达到92.91%最高整体准确率，优于自监督方法且参数量仅为后者的1/7至1/24。在HeliALS数据集（9类，机载激光扫描，仅几何信息）上，实现73.66%整体准确率与50.28%最佳平衡准确率，媲美使用4倍点数的FGI-PointTransformer。跨五类扰动的鲁棒性分析表明各变体互补，适合异质森林环境部署。
原文摘要 · Abstract (English)
Graph-based deep learning on LiDAR point clouds encodes geometry through edge features, yet standard implementations use the same encoding at every scale. In tree species classification, where point density varies by orders of magnitude between trunk and canopy, this is particularly limiting. We prove it is suboptimal: normalized directional features have mean squared error decaying as $\mathcal{O}(1/s^2)$ with inter-point distance~$s$, while raw displacement error is constant, implying each encoding suits a different signal-to-noise ratio (SNR) regime. We propose MS-DGCNN++, a multi-scale dynamic graph convolutional network with \emph{scale-dependent edge encoding}: raw vectors at the local scale (low SNR) and hybrid raw-plus-normalized vectors at the intermediate scale (high SNR). Five ablations validate this design: encoding ablation confirms $+4$--$6\%$ overall accuracy (OA) gain; density dropout shows the flattest degradation under canopy thinning; a noise sweep locates the theoretical crossover near $\text{SNR}_2 \approx 1.22$; max-pooling provenance reveals far neighbors win $85\%$ of competitions under raw encoding, a bias eliminated by normalization; and isotropy analysis shows normalization nearly doubles effective rank. On STPCTLS (seven species, terrestrial laser scanning), MS-DGCNN++ achieves the highest OA ($92.91\%$) among 56 models, surpassing self-supervised methods with $7$--$24\times$ more parameters using only $1.81$M parameters. On HeliALS (nine species, airborne laser scanning, geometry-only), it achieves $73.66\%$ OA with the best balanced accuracy ($50.28\%$), matching FGI-PointTransformer which uses $4\times$ more points. Robustness analysis across five perturbation types reveals complementary variant strengths for deployment in heterogeneous forest environments. Code: https://github.com/said-ohamouddou/MS-DGCNN2.
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。