mlsanityData to 7 Oct 2026

DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds

arXiv 2111.08799 ↗First posted 16 Nov 2021cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Learning from 3D point-cloud data has rapidly gained momentum, motivated by the success of deep learning on images and the increased availability of 3D~data. In this paper, we aim to construct anisotropic convolution layers that work directly on the surface derived from a point cloud. This is challenging because of the lack of a global coordinate system for tangential directions on surfaces. We introduce DeltaConv, a convolution layer that combines geometric operators from vector calculus to enable the construction of anisotropic filters on point clouds. Because these operators are defined on scalar- and vector-fields, we separate the network into a scalar- and a vector-stream, which are connected by the operators. The vector stream enables the network to explicitly represent, evaluate, and process directional information. Our convolutions are robust and simple to implement and match or improve on state-of-the-art approaches on several benchmarks, while also speeding up training and inference.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 72 of its 112 references that are in the map. First posted on arXiv 16 Nov 2021.

Builds on

72 of 112 references.

References · 72

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  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. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  11. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  12. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
38 more
  1. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  2. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  3. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  4. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  5. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  6. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  7. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  8. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  9. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  10. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  11. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
  12. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  13. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  14. 2018Hypergraph Neural Networkscited by 482
  15. 2018Spherical CNNscited by 452
  16. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  17. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  18. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  19. 2019Gauge Equivariant Convolutional Networks and the Icosahedral CNNcited by 262
  20. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  21. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 244
  22. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  23. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  24. 2020DiffusionNet: Discretization Agnostic Learning on Surfacescited by 163
  25. 2017SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernelscited by 160
  26. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  27. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  28. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  29. 2017Pointwise Convolutional Neural Networkscited by 126
  30. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  31. 2016Learning shape correspondence with anisotropic convolutional neural networkscited by 95
  32. 2020Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphscited by 90
  33. 2020A Closer Look at Local Aggregation Operators in Point Cloud Analysiscited by 87
  34. 2018Local Spectral Graph Convolution for Point Set Feature Learningcited by 84
  35. 2019Spherical CNNs on Unstructured Gridscited by 76
  36. 2021Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifoldscited by 72
  37. 2020Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloudcited by 71
  38. 2018RGCNN: Regularized Graph CNN for Point Cloud Segmentationcited by 70

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 2; 2025: 3; 2026: 1.

10 papers.

  1. 2023Understanding and Improving Features Learned in Deep Functional Mapscited by 20
  2. 2024A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentationcited by 14
  3. 2023Toward Mesh-Invariant 3D Generative Deep Learning with Geometric Measurescited by 6
  4. 2025PoissonNet: A Local-Global Approach for Learning on Surfacescited by 6
  5. 2023Basis restricted elastic shape analysis on the space of unregistered surfacescited by 5
  6. 2024Beyond Fixed Topologies: Unregistered Training and Comprehensive Evaluation Metrics for 3D Talking Headscited by 4
  7. 2025Learning Hemodynamic Scalar Fields on Coronary Artery Meshes: A Benchmark of Geometric Deep Learning Modelscited by 2
  8. 2025Neural Descriptors: Self-Supervised Learning of Robust Local Surface Descriptors Using Polynomial Patchescited by 2
  9. 2026Neural Particle Automata: Learning Self-Organizing Particle Dynamicscited by 2
  10. 20233D Understanding of Deformable Linear Objects: Datasets and Transferability Benchmarkcited by 1