mlsanityData to 7 Oct 2026

ZZ-Net: A Universal Rotation Equivariant Architecture for 2D Point Clouds

arXiv 2111.15341 ↗First posted 30 Nov 2021cs.CV cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

In this paper, we are concerned with rotation equivariance on 2D point cloud data. We describe a particular set of functions able to approximate any continuous rotation equivariant and permutation invariant function. Based on this result, we propose a novel neural network architecture for processing 2D point clouds and we prove its universality for approximating functions exhibiting these symmetries. We also show how to extend the architecture to accept a set of 2D-2D correspondences as indata, while maintaining similar equivariance properties. Experiments are presented on the estimation of essential matrices in stereo vision.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 35 of its 56 references that are in the map. First posted on arXiv 30 Nov 2021.

Builds on

35 of 56 references.

References · 35

  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. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2020Point Transformercited by 1,462
  6. 2015Spatial Transformer Networkscited by 1,423
  7. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  8. 2017Deep Setscited by 1,394
  9. 2016Group Equivariant Convolutional Networkscited by 1,154
  10. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  11. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  12. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
23 more
  1. 2019General E(2)-Equivariant Steerable CNNscited by 441
  2. 2018Tune: A Research Platform for Distributed Model Selection and Trainingcited by 395
  3. 2018Invariant and Equivariant Graph Networkscited by 339
  4. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  5. 2016Harmonic Networks: Deep Translation and Rotation Equivariancecited by 293
  6. 2015YFCC100M: The New Data in Multimedia Researchcited by 234
  7. 2017Learning Steerable Filters for Rotation Equivariant CNNscited by 193
  8. 2021A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groupscited by 185
  9. 2019Universal Invariant and Equivariant Graph Neural Networkscited by 182
  10. 2017Learning to Find Good Correspondencescited by 176
  11. 2019On the Universality of Invariant Networkscited by 151
  12. 2019Learning Two-View Correspondences and Geometry Using Order-Aware Networkcited by 148
  13. 2018Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networkscited by 129
  14. 2018Universal approximations of invariant maps by neural networkscited by 127
  15. 2021Scalars are universal: Equivariant machine learning, structured like classical physicscited by 127
  16. 2019On the Limitations of Representing Functions on Setscited by 89
  17. 2020On the Universality of Rotation Equivariant Point Cloud Networkscited by 80
  18. 2021Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifoldscited by 72
  19. 2021Geometric Deep Learning and Equivariant Neural Networkscited by 64
  20. 2020A Wigner-Eckart Theorem for Group Equivariant Convolution Kernelscited by 46
  21. 2021Homogeneous vector bundles and G-equivariant convolutional neural networkscited by 21
  22. 2020Embed Me If You Can: A Geometric Perceptroncited by 10
  23. 2021A simple equivariant machine learning method for dynamics based on scalarscited by 6

Built on by

Cited by year

Citing papers per year: 2022: 7; 2023: 4; 2024: 4.

15 papers.

Sort:

  1. 2022Low Dimensional Invariant Embeddings for Universal Geometric Learningcited by 38
  2. 2022A case for using rotation invariant features in state of the art feature matcherscited by 27
  3. 2022Machine learning and invariant theorycited by 13
  4. 2022A Simple and Universal Rotation Equivariant Point-cloud Networkcited by 11
  5. 2023Normalization-Equivariant Neural Networks with Application to Image Denoisingcited by 11
  6. 2023Complete Neural Networks for Complete Euclidean Graphscited by 10
  7. 2024Weisfeiler Leman for Euclidean Equivariant Machine Learningcited by 10
  8. 2023Investigating how ReLU-networks encode symmetriescited by 8
  9. 2024On the Expressive Power of Sparse Geometric MPNNscited by 7
  10. 2024Affine steerers for structured keypoint descriptioncited by 6
  11. 2023Equivariant geometric convolutions for emulation of dynamical systemscited by 3
  12. 2022TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysiscited by 2
3 more
  1. 2024On normalization-equivariance properties of supervised and unsupervised denoising methods: a surveycited by 1
  2. 2022SIM2E: Benchmarking the Group Equivariant Capability of Correspondence Matching Algorithmscited by 0
  3. 2022In Search of Projectively Equivariant Networkscited by 0