不靠训练参数，用几何编码实现高效点云分类
Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classification
- 用FPS、k-NN和高斯位置编码提取几何特征，无须训练参数
- 在ModelNet40和ScanObjectNN上分别达85.29%和85.89%准确率
- 适合实时、资源受限场景，性能媲美训练模型
本文提出Point-GN，一种用于高效且精确的3D点云分类的非参数化网络。与依赖大量可训练参数的传统深度学习模型不同，Point-GN利用不可学习组件——最远点采样（FPS）、k-近邻（k-NN）和高斯位置编码（GPE）——来提取局部与全局几何特征。该设计无需额外训练即可保持高性能，特别适用于实时、资源受限的应用场景。我们在ModelNet40和ScanObjectNN两个基准数据集上评估Point-GN，分别取得85.29%和85.89%的分类准确率，同时显著降低计算复杂度。Point-GN优于现有非参数方法，并达到全训练模型的性能水平，且所有参数均为零可训练参数。结果表明，Point-GN是实际实时环境中3D点云分类的有力解决方案。
原文摘要 · Abstract (English)
This paper introduces Point-GN, a novel non-parametric network for efficient and accurate 3D point cloud classification. Unlike conventional deep learning models that rely on a large number of trainable parameters, Point-GN leverages non-learnable components-specifically, Farthest Point Sampling (FPS), k-Nearest Neighbors (k-NN), and Gaussian Positional Encoding (GPE)-to extract both local and global geometric features. This design eliminates the need for additional training while maintaining high performance, making Point-GN particularly suited for real-time, resource-constrained applications. We evaluate Point-GN on two benchmark datasets, ModelNet40 and ScanObjectNN, achieving classification accuracies of 85.29% and 85.89%, respectively, while significantly reducing computational complexity. Point-GN outperforms existing non-parametric methods and matches the performance of fully trained models, all with zero learnable parameters. Our results demonstrate that Point-GN is a promising solution for 3D point cloud classification in practical, real-time environments.
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。