arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.03056cs.CVcs.AIcs.LGcs.RO
收藏

Point-GN:一种采用高斯位置编码的用于点云分类的非参数网络

Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classification

Sirjan University of Technology(希尔詹理工大学)

Marzieh Mohammadi, Amir Salarpour

AI总结:

本研究提出零可训练参数的非参数网络Point-GN,通过FPS、k-NN和GPE提取点云几何特征,在ModelNet40、ScanObjectNN上准确率分别达85.29%、85.89%,性能优于现有非参数方法且比肩全训练模型,适用于资源受限的实时3D点云分类场景。

摘要:

本文提出了Point-GN,这是一种用于高效精准3D点云分类的新型非参数网络。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——具体为最远点采样(Farthest Point Sampling, FPS)、k近邻(k-Nearest Neighbors, k-NN)和高斯位置编码(Gaussian Positional Encoding, GPE)——来提取局部和全局几何特征。该设计无需额外训练即可保持高性能,尤其适用于资源受限的实时应用场景。我们在两个基准数据集ModelNet40和ScanObjectNN上评估了Point-GN,其分类准确率分别达到85.29%和85.89%,同时显著降低了计算复杂度。Point-GN在零可训练参数的情况下,性能优于现有非参数方法,且与完全训练模型的表现相当。研究结果表明,Point-GN是实际实时环境下3D点云分类的一种极具潜力的解决方案。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑