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:我们提出了一个非参数网络,用于3D点云分析,Point-NN,它由纯不可测的部件组成:最远点抽样(FPS),K-最近邻(k-NNN)和集成作业,具有三角函数。令人惊讶的是,它在各种3D任务上表现良好,不需要参数或培训,甚至超过现有的完全训练有素的模式。从这一基本的非参数模型开始,我们提议两个扩展。首先,Point-NNN可以作为一个基础建筑框架,通过在顶部插入线性层来构建参数网络。鉴于高端非参数基础,衍生的Point-PN展示了高性能-效率交易,只有很少的可学习参数。第二,Point-NN可以被视为在推断期间已经受过训练的3D模型的插座和玩耍模块。Point-NN可以捕捉补充的几何知识,并在没有再培训的情况下加强现有的3D基准方法。我们希望我们的工作能够给社区带来光,用非参数方法来理解3D点云。代码可在 http://rky/MNSky/Zpors/GINGNCR/GNCR。</s>