Point-LN用无参位置编码实现高效点云分类，参数少、速度快。
Point-LN: A Lightweight Framework for Efficient Point Cloud Classification Using Non-Parametric Positional Encoding
- 融合远点采样与无学习位置编码，构建轻量结构
- 在ModelNet40上达92.1%准确率，参数仅0.3M
- 适合嵌入式设备等资源受限场景实时应用
我们提出Point-LN，一种专为高效三维点云分类设计的轻量化框架。该框架整合了关键的非参数组件——如远点采样（FPS）、k近邻（k-NN）以及不可学习的位置编码——并搭配一个简化的可学习分类器，在显著提升分类准确率的同时保持极小的参数量。这种混合架构确保了低计算开销和快速推理速度，适用于实时及资源受限的应用场景。在ModelNet40和ScanObjectNN等基准数据集上的全面评估表明，Point-LN在性能上可与最先进方法媲美，同时展现出卓越的效率。这些结果确立了Point-LN作为多样点云分类任务中稳健且可扩展的解决方案，凸显其在各类计算机视觉应用中的广泛潜力。
原文摘要 · Abstract (English)
We introduce Point-LN, a novel lightweight framework engineered for efficient 3D point cloud classification. Point-LN integrates essential non-parametric components-such as Farthest Point Sampling (FPS), k-Nearest Neighbors (k-NN), and non-learnable positional encoding-with a streamlined learnable classifier that significantly enhances classification accuracy while maintaining a minimal parameter footprint. This hybrid architecture ensures low computational costs and rapid inference speeds, making Point-LN ideal for real-time and resource-constrained applications. Comprehensive evaluations on benchmark datasets, including ModelNet40 and ScanObjectNN, demonstrate that Point-LN achieves competitive performance compared to state-of-the-art methods, all while offering exceptional efficiency. These results establish Point-LN as a robust and scalable solution for diverse point cloud classification tasks, highlighting its potential for widespread adoption in various computer vision applications.
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。