mlsanityData to 14 Oct 2026

Enhancing Local Geometry Learning for 3D Point Cloud via Decoupling Convolution

arXiv 2207.01181 ↗First posted 4 Jul 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Modeling the local surface geometry is challenging in 3D point cloud understanding due to the lack of connectivity information. Most prior works model local geometry using various convolution operations. We observe that the convolution can be equivalently decomposed as a weighted combination of a local and a global component. With this observation, we explicitly decouple these two components so that the local one can be enhanced and facilitate the learning of local surface geometry. Specifically, we propose Laplacian Unit (LU), a simple yet effective architectural unit that can enhance the learning of local geometry. Extensive experiments demonstrate that networks equipped with LUs achieve competitive or superior performance on typical point cloud understanding tasks. Moreover, through establishing connections between the mean curvature flow, a further investigation of LU based on curvatures is made to interpret the adaptive smoothing and sharpening effect of LU. The code will be available.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 48 of its 73 references that are in the map. First posted on arXiv 4 Jul 2022.

Builds on

48 of 73 references.

References · 48

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  7. 2017Squeeze-and-Excitation Networkscited by 4,789
  8. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  9. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  10. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  11. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  12. 2020Point Transformercited by 1,470
36 more
  1. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  2. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  3. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  4. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  5. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  6. 2020PCT: Point cloud transformercited by 732
  7. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  8. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  9. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  10. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  11. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  12. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  13. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  14. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 310
  15. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 239
  16. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  17. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 179
  18. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  19. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  20. 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
  21. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  22. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  23. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  24. 2020MVTN: Multi-View Transformation Network for 3D Shape Recognitioncited by 140
  25. 2017Pointwise Convolutional Neural Networkscited by 127
  26. 2020Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Reviewcited by 108
  27. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  28. 2020A Closer Look at Local Aggregation Operators in Point Cloud Analysiscited by 87
  29. 2019Interpolated Convolutional Networks for 3D Point Cloud Understandingcited by 86
  30. 2021Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusioncited by 72
  31. 2017Multi-level Residual Networks from Dynamical Systems Viewcited by 59
  32. 2014Rigid-Motion Scattering for Texture Classificationcited by 52
  33. 2018Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNNcited by 33
  34. 2021Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoningcited by 22
  35. 2022Enhancing Local Feature Learning for 3D Point Cloud Processing using Unary-Pairwise Attentioncited by 4
  36. 2022SnapshotNet: Self-supervised Feature Learning for Point Cloud Data Segmentation Using Minimal Labeled Datacited by 3

Built on by

Not cited yet.