NPNet: A Non-Parametric Network with Adaptive Gaussian-Fourier Positional Encoding for 3D Classification and Segmentation
Abstract
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
Cite
@article{arxiv.2602.00542,
title = {NPNet: A Non-Parametric Network with Adaptive Gaussian-Fourier Positional Encoding for 3D Classification and Segmentation},
author = {Mohammad Saeid and Amir Salarpour and Pedram MohajerAnsari and Mert D. Pesé},
journal= {arXiv preprint arXiv:2602.00542},
year = {2026}
}
Comments
Accepted to the 2026 IEEE Intelligent Vehicles Symposium (IV 2026)