mlsanityData to 7 Oct 2026

diffConv: Analyzing Irregular Point Clouds with an Irregular View

arXiv 2111.14658 ↗First posted 29 Nov 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Standard spatial convolutions assume input data with a regular neighborhood structure. Existing methods typically generalize convolution to the irregular point cloud domain by fixing a regular "view" through e.g. a fixed neighborhood size, where the convolution kernel size remains the same for each point. However, since point clouds are not as structured as images, the fixed neighbor number gives an unfortunate inductive bias. We present a novel graph convolution named Difference Graph Convolution (diffConv), which does not rely on a regular view. diffConv operates on spatially-varying and density-dilated neighborhoods, which are further adapted by a learned masked attention mechanism. Experiments show that our model is very robust to the noise, obtaining state-of-the-art performance in 3D shape classification and scene understanding tasks, along with a faster inference speed.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 35 of its 52 references that are in the map. First posted on arXiv 29 Nov 2021.

Builds on

35 of 52 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  8. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  9. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  10. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  11. 2019Simplifying Graph Convolutional Networkscited by 1,470
  12. 2020Point Transformercited by 1,462
23 more
  1. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  2. 2020PCT: Point cloud transformercited by 730
  3. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  4. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  5. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  6. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  7. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  8. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  9. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  10. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  11. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  12. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  13. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  14. 2020A Closer Look at Local Aggregation Operators in Point Cloud Analysiscited by 87
  15. 2018Local Spectral Graph Convolution for Point Set Feature Learningcited by 84
  16. 2020Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadwayscited by 77
  17. 2020Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloudcited by 71
  18. 2016SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentationcited by 70
  19. 2018RGCNN: Regularized Graph CNN for Point Cloud Segmentationcited by 70
  20. 2019A-CNN: Annularly Convolutional Neural Networks on Point Cloudscited by 66
  21. 2021Adaptive Graph Convolution for Point Cloud Analysiscited by 60
  22. 2016A Convolutional Encoder Model for Neural Machine Translationcited by 54
  23. 20183DTI-Net: Learn Inner Transform Invariant 3D Geometry Features using Dynamic GCNcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 1; 2024: 1.

6 papers.

  1. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  2. 20223DCTN: 3D Convolution-Transformer Network for Point Cloud Classificationcited by 25
  3. 2022AGConv: Adaptive Graph Convolution on 3D Point Cloudscited by 13
  4. 2023Dynamic Clustering Transformer Network for Point Cloud Segmentationcited by 2
  5. 2024Graph Neural Networks in Intelligent Transportation Systems: Advances, Applications and Trendscited by 1
  6. 20223DGTN: 3D Dual-Attention GLocal Transformer Network for Point Cloud Classification and Segmentationcited by 0