Modern depth sensors such as LiDAR operate by sweeping laser-beams across the scene, resulting in a point cloud with notable 1D curve-like structures. In this work, we introduce a new point cloud processing scheme and backbone, called CurveCloudNet, which takes advantage of the curve-like structure inherent to these sensors. While existing backbones discard the rich 1D traversal patterns and rely on Euclidean operations, CurveCloudNet parameterizes the point cloud as a collection of polylines (dubbed a "curve cloud"), establishing a local surface-aware ordering on the points. Our method applies curve-specific operations to process the curve cloud, including a symmetric 1D convolution, a ball grouping for merging points along curves, and an efficient 1D farthest point sampling algorithm on curves. By combining these curve operations with existing point-based operations, CurveCloudNet is an efficient, scalable, and accurate backbone with low GPU memory requirements. Evaluations on the ShapeNet, Kortx, Audi Driving, and nuScenes datasets demonstrate that CurveCloudNet outperforms both point-based and sparse-voxel backbones in various segmentation settings, notably scaling better to large scenes than point-based alternatives while exhibiting better single object performance than sparse-voxel alternatives.

翻译：现代深度传感器（如LiDAR）通过向场景扫描激光束进行工作，由此产生的点云呈现出显著的一维曲线状结构。本文提出了一种新的点云处理方案和主干网络——CurveCloudNet，该网络利用了这些传感器固有的曲线结构特性。现有主干网络丢弃了丰富的一维遍历模式，并依赖于欧几里得操作，而CurveCloudNet则将点云参数化为多段线集合（称为"曲线云"），在点上建立了局部曲面感知排序。我们的方法应用曲线专用操作来处理曲线云，包括对称一维卷积、沿曲线合并点的球体分组，以及针对曲线的高效一维最远点采样算法。通过将这些曲线操作与现有基于点的操作相结合，CurveCloudNet成为一种高效、可扩展且准确的主干网络，且GPU内存需求低。在ShapeNet、Kortx、Audi Driving和nuScenes数据集上的评估表明，CurveCloudNet在各种分割设置中均优于基于点和稀疏体素的主干网络，特别是在大规模场景中比基于点的方法具有更好的扩展性，同时在单个物体性能上优于稀疏体素方法。