mlsanityData to 7 Oct 2026

NPNet: A Non-Parametric Network with Adaptive Gaussian-Fourier Positional Encoding for 3D Classification and Segmentation

arXiv 2602.00542 ↗First posted 31 Jan 2026cs.CV cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

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

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 35 of its 50 references that are in the map. First posted on arXiv 31 Jan 2026.

Builds on

35 of 50 references.

References · 35

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  6. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  7. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  8. 2020PCT: Point cloud transformercited by 730
  9. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  10. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  11. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  12. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
23 more
  1. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  2. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  3. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  4. 2020Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Reviewcited by 114
  5. 2020Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Reviewcited by 107
  6. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 105
  7. 2023PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstructioncited by 84
  8. 2019PointHop: An Explainable Machine Learning Method for Point Cloud Classificationcited by 46
  9. 2022Meta Architecture for Point Cloud Analysiscited by 39
  10. 2023Attention-based Point Cloud Edge Samplingcited by 37
  11. 2023Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysiscited by 34
  12. 2022Transformers in 3D Point Clouds: A Surveycited by 31
  13. 2021R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Methodcited by 26
  14. 2021PointAcc: Efficient Point Cloud Acceleratorcited by 23
  15. 2024Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classificationcited by 8
  16. 2024Thermal Image Calibration and Correction using Unpaired Cycle-Consistent Adversarial Networkscited by 5
  17. 2025Real-Time LiDAR Point Cloud Compression and Transmission for Resource-constrained Robotscited by 5
  18. 2022Projection-based Point Convolution for Efficient Point Cloud Segmentationcited by 4
  19. 2025Point-LN: A Lightweight Framework for Efficient Point Cloud Classification Using Non-Parametric Positional Encodingcited by 3
  20. 2025Enhancing 3D Point Cloud Classification with ModelNet-R and Point-SkipNetcited by 3
  21. 2023GLHAD: A Group Lasso-based Hybrid Attack Detection and Localization Framework for Multistage Manufacturing Systemscited by 1
  22. 2023PointeNet: A Lightweight Framework for Effective and Efficient Point Cloud Analysiscited by 1
  23. 2025PointODE: Lightweight Point Cloud Learning with Neural Ordinary Differential Equations on Edgecited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026SLNet: A Super-Lightweight Geometry-Adaptive Network for 3D Point Cloud Recognitioncited by 1