用数学预处理+轻量网络，高效学习点云曲率
CanonNet: Canonical Ordering and Curvature Learning for Point Cloud Analysis
- 先通过数学方法建立统一点序和朝向，再用合成曲面训练网络
- 曲率估计性能领先，参数量比同类方法少100倍
- 适合资源受限的实时点云分析场景
点云处理面临两大挑战：建立一致的点序和有效学习细粒度几何特征。现有架构依赖复杂操作，表达能力受限且难以捕捉精细表面结构。我们提出CanonNet，一种由两个互补模块组成的轻量级神经网络：(1) 预处理流程生成规范化的点序和方向；(2) 几何学习框架在具有精确曲率值的合成表面上训练网络。该模块化设计无需复杂的变换不变架构，即可有效捕获局部几何特性。实验表明，CanonNet在曲率估计上达到最先进水平，在几何描述子任务中表现优异，参数量仅为同类方法的1/100。其高效性使其特别适用于计算资源受限的实际应用，证明了数学预处理能有效补充神经架构进行点云分析。代码已公开。
原文摘要 · Abstract (English)
Point cloud processing poses two fundamental challenges: establishing consistent point ordering and effectively learning fine-grained geometric features. Current architectures rely on complex operations that limit expressivity while struggling to capture detailed surface geometry. We present CanonNet, a lightweight neural network composed of two complementary components: (1) a preprocessing pipeline that creates a canonical point ordering and orientation, and (2) a geometric learning framework where networks learn from synthetic surfaces with precise curvature values. This modular approach eliminates the need for complex transformation-invariant architectures while effectively capturing local geometric properties. Our experiments demonstrate state-of-the-art performance in curvature estimation and competitive results in geometric descriptor tasks with significantly fewer parameters (\textbf{100X}) than comparable methods. CanonNet's efficiency makes it particularly suitable for real-world applications where computational resources are limited, demonstrating that mathematical preprocessing can effectively complement neural architectures for point cloud analysis. The code for the project is publicly available \hyperlink{https://benjyfri.github.io/CanonNet/}{https://benjyfri.github.io/CanonNet/}.
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。