Thanks to the application of deep learning technology in point cloud processing of the remote sensing field, point cloud classification has become a research hotspot in recent years. Although existing solutions have made unprecedented progress, they ignore the inherent characteristics of point clouds in remote sensing fields that are strictly arranged according to latitude, longitude, and altitude, which brings great convenience to the segmentation of point clouds in remote sensing fields. To consider this property cleverly, we propose novel convolution operators, termed Twin Deformable point Convolutions (TDConvs), which aim to achieve adaptive feature learning by learning deformable sampling points in the latitude–longitude plane and altitude direction, respectively. First, to model the characteristics of the latitude–longitude plane, we propose a Cylinder-wise Deformable point Convolution (CyDConv) operator, which generates a two-dimensional cylinder map by constructing a cylinder-like grid in the latitude–longitude direction, and then performs adaptive feature sampling on the cylinder map by deformable offset learning. Furthermore, to better integrate the features of the latitude–longitude plane and the spatial geometric features, we perform a multi-scale fusion of the extracted latitude–longitude features and spatial geometric features, and realize it through the aggregation of adjacent point features of different scales. In addition, a Sphere-wise Deformable point Convolution (SpDConv) operator is introduced to adaptively offset the sampling points in three-dimensional space by constructing a sphere grid structure, aiming at modeling the characteristics in the altitude direction. Experiments on existing popular benchmarks conclude that our TDConvs achieve the best segmentation performance, surpassing existing advanced methods such as RFFS-Net and MCFN. Specifically, TDConvs achieves 73.4% mF1 on the ISPRS Vaihingen 3D dataset, which is 4.8% higher than the baseline. Details of the datasets used and the code is available on https://github.com/WingkeungM/TDConvs.

中文翻译：

---

用于机载激光扫描点云分类的双可变形点卷积


得益于深度学习技术在遥感领域点云处理中的应用，点云分类成为近年来的研究热点。虽然现有的解决方案取得了前所未有的进步，但它们忽略了遥感领域点云严格按照纬度、经度、海拔高度排列的固有特性，这给遥感领域点云的分割带来了极大的便利。为了巧妙地考虑这一特性，我们提出了新的卷积算子，称为双可变形点卷积 （TDConvs），旨在通过分别学习经纬面和高度方向的可变形采样点来实现自适应特征学习。首先，为了模拟经纬面的特征，我们提出了一个圆柱形可变形点卷积（CyDConv）算子，通过在经纬方向上构造一个圆柱状网格来生成二维圆柱体图，然后通过可变形偏移学习对圆柱体图进行自适应特征采样。此外，为了更好地融合经纬面特征和空间几何特征，我们将提取的经纬度特征和空间几何特征进行多尺度融合，并通过不同尺度的相邻点特征的聚合来实现。此外，该文还引入了球体可变形点卷积（SpDConv）算子，通过构建球形网格结构来自适应偏移三维空间中的采样点，旨在对高度方向的特征进行建模。 对现有流行基准的实验得出结论，我们的 TDConvs 实现了最佳的分割性能，超过了现有的 RFFS-Net 和 MCFN 等先进方法。具体来说，TDConvs 在 ISPRS Vaihingen 3D 数据集上实现了 73.4% 的 mF1，比基线高出 4.8%。有关使用的数据集和代码的详细信息，请访问 https://github.com/WingkeungM/TDConvs。