无需参数的3D点云分类分割新方法，自适应位置编码提升稳定性
NPNet: A Non-Parametric Network with Adaptive Gaussian-Fourier Positional Encoding for 3D Classification and Segmentation
- 用确定性操作构建特征，无任何可学习权重
- 自适应高斯-傅里叶编码根据输入几何调整参数，跨尺度稳定
- 少样本下表现优异，内存与推理开销小，适合资源受限场景
我们提出NPNet，一种完全非参数化的3D点云分类与部件分割方法。该方法不包含任何可学习权重，而是通过最远点采样、k近邻和池化等确定性算子构建点特征。核心思想是自适应高斯-傅里叶位置编码，其带宽和高斯-余弦混合比例由输入几何动态决定，使模型在不同尺度和采样密度下保持稳定。针对分割任务，额外引入固定频率傅里叶特征以提供全局上下文信息。在ModelNet40/ModelNet-R、ScanObjectNN和ShapeNetPart数据集上，NPNet在非参数基线中表现强劲，尤其在ModelNet40的少样本设置下优势显著。相比以往非参数方法，其内存占用和推理时间也更优。
原文摘要 · Abstract (English)
We present NPNet, a fully non-parametric approach for 3D point-cloud classification and part segmentation. NPNet contains no learned weights; instead, it builds point features using deterministic operators such as farthest point sampling, k-nearest neighbors, and pooling. Our key idea is an adaptive Gaussian-Fourier positional encoding whose bandwidth and Gaussian-cosine mixing are chosen from the input geometry, helping the method remain stable across different scales and sampling densities. For segmentation, we additionally incorporate fixed-frequency Fourier features to provide global context alongside the adaptive encoding. Across ModelNet40/ModelNet-R, ScanObjectNN, and ShapeNetPart, NPNet achieves strong performance among non-parametric baselines, and it is particularly effective in few-shot settings on ModelNet40. NPNet also offers favorable memory use and inference time compared to prior non-parametric methods
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。