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

• URL: http://arxiv.org/abs/2603.07454v1
• Date: Sun, 08 Mar 2026 04:07:42 GMT
• Title: SLNet: A Super-Lightweight Geometry-Adaptive Network for 3D Point Cloud Recognition
• Abstract summary: We present SLNet, a lightweight backbone for 3D point cloud recognition.<n>The model is built on two simple ideas: NAPE (Nonparametric Adaptive Point Embedding) and GMU (Geometric Modulation Unit)
• Score: 1.499944454332829
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Lightweight Complementary-Cue Fusion for Robust Video Face Forgery Detection [16.800905609731178]
  We show that a single, lightweight fusion of two handcrafted cues can achieve higher accuracy with a much smaller model.<n>Based on the Xception baseline model, we build two detectors: LFWS, which adds a 1x1 convolution to combine a low-frequency Wavelet-Denoised Feature (WDF) with a phase-spectrum channel.
  arXiv  Detail & Related papers  (2026-05-27T20:51:04Z)
• VeloxNet: Efficient Spatial Gating for Lightweight Embedded Image Classification [1.9903316442426757]
  This paper introduces VeloxNet, a lightweight CNN architecture that replaces SqueezeNet's fire modules with gated multi-layer perceptron blocks for embedded image classification.<n>We evaluate VeloxNet on three aerial image datasets.
  arXiv  Detail & Related papers  (2026-03-19T21:46:20Z)
• Efficient Point Cloud Processing with High-Dimensional Positional Encoding and Non-Local MLPs [68.55902504866422]
  We develop a two-stage abstraction and refinement (ABSREF) view for modular feature extraction in point cloud processing.<n>We propose a High-stage Positional (HPE) module to explicitly utilize positional information.<n>Within our ABSREF view, we rethink local aggregation in relationships and propose replacing time-consuming local operations.
  arXiv  Detail & Related papers  (2026-03-04T14:12:13Z)
• NPNet: A Non-Parametric Network with Adaptive Gaussian-Fourier Positional Encoding for 3D Classification and Segmentation [1.499944454332829]
  NPNet is a non-parametric approach for 3D point-cloud classification and part segmentation.<n>It builds point features using deterministic operators such as farthest point sampling, k-nearest neighbors, and pooling.<n>It offers favorable memory use and inference time compared to prior non-parametric methods.
  arXiv  Detail & Related papers  (2026-01-31T06:16:19Z)
• HLS4PC: A Parametrizable Framework For Accelerating Point-Based 3D Point Cloud Models on FPGA [2.762332196350206]
  3D point cloud models execute computation and memory intensive mapping functions alongside NN layers for classification/segmentation.<n>PointMLP-Lite is a 4x less complex variant with only 2% accuracy drop on ModelNet40.<n>Our implementation achieves 2.3x and 22x higher throughput compared to the GPU and CPU implementations, respectively.
  arXiv  Detail & Related papers  (2025-12-11T17:09:12Z)
• LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling [47.94285833315427]
  We propose a Locally constrained Compact point cloud Model (LCM) consisting of a locally constrained compact encoder and a locally constrained Mamba-based decoder. Our encoder replaces self-attention with our local aggregation layers to achieve an elegant balance between performance and efficiency. This decoder ensures linear complexity while maximizing the perception of point cloud geometry information from unmasked patches with higher information density.
  arXiv  Detail & Related papers  (2024-05-27T13:19:23Z)
• ParFormer: A Vision Transformer with Parallel Mixer and Sparse Channel Attention Patch Embedding [9.144813021145039]
  This paper introduces ParFormer, a vision transformer that incorporates a Parallel Mixer and a Sparse Channel Attention Patch Embedding (SCAPE) ParFormer improves feature extraction by combining convolutional and attention mechanisms. For edge device deployment, ParFormer-T excels with a throughput of 278.1 images/sec, which is 1.38 $times$ higher than EdgeNeXt-S. The larger variant, ParFormer-L, reaches 83.5% Top-1 accuracy, offering a balanced trade-off between accuracy and efficiency.
  arXiv  Detail & Related papers  (2024-03-22T07:32:21Z)
• Lightweight and Progressively-Scalable Networks for Semantic Segmentation [100.63114424262234]
  Multi-scale learning frameworks have been regarded as a capable class of models to boost semantic segmentation. In this paper, we thoroughly analyze the design of convolutional blocks and the ways of interactions across multiple scales. We devise Lightweight and Progressively-Scalable Networks (LPS-Net) that novelly expands the network complexity in a greedy manner.
  arXiv  Detail & Related papers  (2022-07-27T16:00:28Z)
• Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework [55.40001810884942]
  We introduce a pure residual network, called PointMLP, which integrates no sophisticated local geometrical extractors but still performs very competitively. On the real-world ScanObjectNN dataset, our method even surpasses the prior best method by 3.3% accuracy. Compared to most recent CurveNet, PointMLP trains 2x faster, tests 7x faster, and is more accurate on ModelNet40 benchmark.
  arXiv  Detail & Related papers  (2022-02-15T01:39:07Z)
• Compact Multi-level Sparse Neural Networks with Input Independent Dynamic Rerouting [33.35713740886292]
  Sparse deep neural networks can substantially reduce the complexity and memory consumption of the models. Facing the real-life challenges, we propose to train a sparse model that supports multiple sparse levels. In this way, one can dynamically select the appropriate sparsity level during inference, while the storage cost is capped by the least sparse sub-model.
  arXiv  Detail & Related papers  (2021-12-21T01:35:51Z)
• DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers [105.74546828182834]
  We show a hardware-efficient dynamic inference regime, named dynamic weight slicing, which adaptively slice a part of network parameters for inputs with diverse difficulty levels. We present dynamic slimmable network (DS-Net) and dynamic slice-able network (DS-Net++) by input-dependently adjusting filter numbers of CNNs and multiple dimensions in both CNNs and transformers.
  arXiv  Detail & Related papers  (2021-09-21T09:57:21Z)
• Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling [52.464516118826765]
  We introduce RandLA-Net, an efficient and lightweight neural architecture to infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Our RandLA-Net can process 1 million points in a single pass up to 200x faster than existing approaches.
  arXiv  Detail & Related papers  (2021-07-06T05:08:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.