mlsanityData to 14 Oct 2026

SLNet: A Super-Lightweight Geometry-Adaptive Network for 3D Point Cloud Recognition

arXiv 2603.07454 ↗First posted 8 Mar 2026cs.CV cs.LG cs.ROcited by 1

Not on the map. Why?

Abstract (arXiv)

We present SLNet, a lightweight backbone for 3D point cloud recognition designed to achieve strong performance without the computational cost of many recent attention, graph, and deep MLP based models. The model is built on two simple ideas: NAPE (Nonparametric Adaptive Point Embedding), which captures spatial structure using a combination of Gaussian RBF and cosine bases with input adaptive bandwidth and blending, and GMU (Geometric Modulation Unit), a per channel affine modulator that adds only 2D learnable parameters. These components are used within a four stage hierarchical encoder with FPS+kNN grouping, nonparametric normalization, and shared residual MLPs. In experiments, SLNet shows that a very small model can still remain highly competitive across several 3D recognition tasks. On ModelNet40, SLNet-S with 0.14M parameters and 0.31 GFLOPs achieves 93.64% overall accuracy, outperforming PointMLP-elite with 5x fewer parameters, while SLNet-M with 0.55M parameters and 1.22 GFLOPs reaches 93.92%, exceeding PointMLP with 24x fewer parameters. On ScanObjectNN, SLNet-M achieves 84.25% overall accuracy within 1.2 percentage points of PointMLP while using 28x fewer parameters. For large scale scene segmentation, SLNet-T extends the backbone with local Point Transformer attention and reaches 58.2% mIoU on S3DIS Area 5 with only 2.5M parameters, more than 17x fewer than Point Transformer V3. We also introduce NetScore+, which extends NetScore by incorporating latency and peak memory so that efficiency can be evaluated in a more deployment oriented way. Across multiple benchmarks and hardware settings, SLNet delivers a strong overall balance between accuracy and efficiency. Code is available at: https://github.com/m-saeid/SLNet.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 30 of its 36 references that are in the map. First posted on arXiv 8 Mar 2026.

Builds on

30 of 36 references.

References · 30

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  4. 2020Point Transformercited by 1,470
  5. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  6. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  7. 2020PCT: Point cloud transformercited by 732
  8. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  9. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  10. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  11. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  12. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
18 more
  1. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  2. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  3. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  4. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  5. 2020Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Reviewcited by 116
  6. 2020Self-Supervised Few-Shot Learning on Point Cloudscited by 66
  7. 2024Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysiscited by 53
  8. 2023Attention-based Point Cloud Edge Samplingcited by 37
  9. 2023Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysiscited by 34
  10. 2020PointHop++: A Lightweight Learning Model on Point Sets for 3D Classificationcited by 22
  11. 2024Parameter-efficient Prompt Learning for 3D Point Cloud Understandingcited by 16
  12. 2024Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classificationcited by 8
  13. 2024Graph Construction with Flexible Nodes for Traffic Demand Predictioncited by 3
  14. 2025Point-LN: A Lightweight Framework for Efficient Point Cloud Classification Using Non-Parametric Positional Encodingcited by 3
  15. 2025Enhancing 3D Point Cloud Classification with ModelNet-R and Point-SkipNetcited by 3
  16. 2025PointDiffuse: A Dual-Conditional Diffusion Model for Enhanced Point Cloud Semantic Segmentationcited by 2
  17. 2020DV-ConvNet: Fully Convolutional Deep Learning on Point Clouds with Dynamic Voxelization and 3D Group Convolutioncited by 1
  18. 2026NPNet: A Non-Parametric Network with Adaptive Gaussian-Fourier Positional Encoding for 3D Classification and Segmentationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Efficient PEFT Methods with Adaptive Checkpointing for Vision Models and VLMs on Resource Constrained Consumer-GPUscited by 1