We present a Non-parametric Network for 3D point cloud analysis, Point-NN, which consists of purely non-learnable components: farthest point sampling (FPS), k-nearest neighbors (k-NN), and pooling operations, with trigonometric functions. Surprisingly, it performs well on various 3D tasks, requiring no parameters or training, and even surpasses existing fully trained models. Starting from this basic non-parametric model, we propose two extensions. First, Point-NN can serve as a base architectural framework to construct Parametric Networks by simply inserting linear layers on top. Given the superior non-parametric foundation, the derived Point-PN exhibits a high performance-efficiency trade-off with only a few learnable parameters. Second, Point-NN can be regarded as a plug-and-play module for the already trained 3D models during inference. Point-NN captures the complementary geometric knowledge and enhances existing methods for different 3D benchmarks without re-training. We hope our work may cast a light on the community for understanding 3D point clouds with non-parametric methods. Code is available at https://github.com/ZrrSkywalker/Point-NN.

翻译：我们提出了一种用于三维点云分析的非参数网络Point-NN，该网络仅由不可学习的组件构成：最远点采样（FPS）、k近邻（k-NN）和池化操作，并辅以三角函数。令人惊讶的是，该网络在多种三维任务上表现优异，无需任何参数或训练，甚至超越了现有的完全训练模型。基于这一基础非参数模型，我们提出了两个扩展方案。首先，Point-NN可作为基础架构框架，通过简单地在顶层插入线性层来构建参数网络。凭借其优越的非参数基础，由此推导出的Point-PN仅使用少量可学习参数即可实现高性能与效率的平衡。其次，Point-NN可被视为一个即插即用模块，在推理阶段集成到已训练好的三维模型中。Point-NN能够捕捉互补的几何知识，无需重新训练即可增强现有方法在不同三维基准测试上的性能。我们希望本研究能为学界利用非参数方法理解三维点云提供新的视角。代码开源地址：https://github.com/ZrrSkywalker/Point-NN。