mlsanityData to 7 Oct 2026

SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation

arXiv 2209.05924 ↗First posted 13 Sep 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Efficiency and robustness are increasingly needed for applications on 3D point clouds, with the ubiquitous use of edge devices in scenarios like autonomous driving and robotics, which often demand real-time and reliable responses. The paper tackles the challenge by designing a general framework to construct 3D learning architectures with SO(3) equivariance and network binarization. However, a naive combination of equivariant networks and binarization either causes sub-optimal computational efficiency or geometric ambiguity. We propose to locate both scalar and vector features in our networks to avoid both cases. Precisely, the presence of scalar features makes the major part of the network binarizable, while vector features serve to retain rich structural information and ensure SO(3) equivariance. The proposed approach can be applied to general backbones like PointNet and DGCNN. Meanwhile, experiments on ModelNet40, ShapeNet, and the real-world dataset ScanObjectNN, demonstrated that the method achieves a great trade-off between efficiency, rotation robustness, and accuracy. The codes are available at https://github.com/zhuoinoulu/svnet.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 44 of its 55 references that are in the map. First posted on arXiv 13 Sep 2022.

Builds on

44 of 55 references.

References · 44

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  8. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  9. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  10. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  11. 2016Group Equivariant Convolutional Networkscited by 1,154
  12. 2021E(n) Equivariant Graph Neural Networkscited by 951
32 more
  1. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  2. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  3. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  4. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  5. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
  6. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  7. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  8. 2018Spherical CNNscited by 452
  9. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
  10. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 348
  11. 2020Learning from Protein Structure with Geometric Vector Perceptronscited by 308
  12. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  13. 2016Steerable CNNscited by 298
  14. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 244
  15. 2017Learning Steerable Filters for Rotation Equivariant CNNscited by 193
  16. 2020ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functionscited by 183
  17. 2020Training Binary Neural Networks with Real-to-Binary Convolutionscited by 111
  18. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  19. 2021Equivariant Point Network for 3D Point Cloud Analysiscited by 81
  20. 2019Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 80
  21. 2020A Rotation-Invariant Framework for Deep Point Cloud Analysiscited by 62
  22. 2018CubeNet: Equivariance to 3D Rotation and Translationcited by 59
  23. 2021Equivariant Graph Neural Networks for 3D Macromolecular Structurecited by 53
  24. 2020Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloudcited by 38
  25. 20193D-Rotation-Equivariant Quaternion Neural Networkscited by 30
  26. 2020BiPointNet: Binary Neural Network for Point Cloudscited by 30
  27. 2020Global Context Aware Convolutions for 3D Point Cloud Understandingcited by 26
  28. 2020Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysiscited by 22
  29. 2021Frame Averaging for Equivariant Shape Space Learningcited by 18
  30. 2021Dynamic Binary Neural Network by learning channel-wise thresholdscited by 13
  31. 2019Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topologycited by 11
  32. 2020A Review of Recent Advances of Binary Neural Networks for Edge Computingcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 3; 2025: 3.

10 papers.

  1. 2025Rapid Salient Object Detection with Difference Convolutional Neural Networkscited by 9
  2. 2024Local-consistent Transformation Learning for Rotation-invariant Point Cloud Analysiscited by 6
  3. 2024An intuitive multi-frequency feature representation for SO(3)-equivariant networkscited by 5
  4. 2025Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learningcited by 5
  5. 2023Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolutioncited by 3
  6. 2023BPT: Binary Point Cloud Transformer for Place Recognitioncited by 1
  7. 2023From Local Binary Patterns to Pixel Difference Networks for Efficient Visual Representation Learningcited by 1
  8. 2024FBPT: A Fully Binary Point Transformercited by 1
  9. 2023ARBiBench: Benchmarking Adversarial Robustness of Binarized Neural Networkscited by 0
  10. 2025Hierarchical Direction Perception via Atomic Dot-Product Operators for Rotation-Invariant Point Clouds Learningcited by 0