mlsanityData to 7 Oct 2026

Towards Efficient Graph Convolutional Networks for Point Cloud Handling

arXiv 2104.05706 ↗First posted 12 Apr 2021cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

In this paper, we aim at improving the computational efficiency of graph convolutional networks (GCNs) for learning on point clouds. The basic graph convolution that is typically composed of a K-nearest neighbor (KNN) search and a multilayer perceptron (MLP) is examined. By mathematically analyzing the operations there, two findings to improve the efficiency of GCNs are obtained. (1) The local geometric structure information of 3D representations propagates smoothly across the GCN that relies on KNN search to gather neighborhood features. This motivates the simplification of multiple KNN searches in GCNs. (2) Shuffling the order of graph feature gathering and an MLP leads to equivalent or similar composite operations. Based on those findings, we optimize the computational procedure in GCNs. A series of experiments show that the optimized networks have reduced computational complexity, decreased memory consumption, and accelerated inference speed while maintaining comparable accuracy for learning on point clouds. Code will be available at urlhttps://github.com/ofsoundof/EfficientGCN.git.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 52 of its 61 references that are in the map. First posted on arXiv 12 Apr 2021.

Builds on

52 of 61 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2014Going Deeper with Convolutionscited by 4,231
  8. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  9. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  10. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  11. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  12. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
38 more
  1. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  2. 2020Point Transformercited by 1,462
  3. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  4. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  5. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  6. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  7. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  8. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  9. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  10. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  11. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  12. 2020Convolutional Occupancy Networkscited by 760
  13. 2020PCT: Point cloud transformercited by 730
  14. 2018Open3D: A Modern Library for 3D Data Processingcited by 717
  15. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  16. 2018Rethinking the Value of Network Pruningcited by 595
  17. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  18. 2019Graph Transformer Networkscited by 520
  19. 2019Similarity-Preserving Knowledge Distillationcited by 507
  20. 2019Graph U-Netscited by 489
  21. 2019Self-Attention Graph Poolingcited by 421
  22. 2019Hyperbolic Graph Convolutional Neural Networkscited by 400
  23. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  24. 2019Exact Combinatorial Optimization with Graph Convolutional Neural Networkscited by 313
  25. 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 226
  26. 2016Trained Ternary Quantizationcited by 203
  27. 2015Accelerating Very Deep Convolutional Networks for Classification and Detectioncited by 109
  28. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  29. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  30. 2020Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compressioncited by 72
  31. 2019Learning Filter Basis for Convolutional Neural Network Compressioncited by 57
  32. 2020DHP: Differentiable Meta Pruning via HyperNetworkscited by 57
  33. 2020CaSPR: Learning Canonical Spatiotemporal Point Cloud Representationscited by 51
  34. 2019Quaternion Equivariant Capsule Networks for 3D Point Cloudscited by 41
  35. 2019Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Featurescited by 31
  36. 2020ShapeFlow: Learnable Deformations Among 3D Shapescited by 28
  37. 2016FPNN: Field Probing Neural Networks for 3D Datacited by 25
  38. 2020Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometrycited by 18

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 4; 2024: 4; 2025: 3; 2026: 3.

18 papers.

Sort:

  1. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  2. 2022PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detectioncited by 33
  3. 2023Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognitioncited by 13
  4. 2023Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platformscited by 12
  5. 2023Decoupled Local Aggregation for Point Cloud Learningcited by 12
  6. 2021Towards Efficient Point Cloud Graph Neural Networks Through Architectural Simplificationcited by 9
  7. 2024A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectivenesscited by 6
  8. 2021Haar Wavelet Feature Compression for Quantized Graph Convolutional Networkscited by 5
  9. 2024Graph Neural Networks Automated Design and Deployment on Device-Edge Co-Inference Systemscited by 5
  10. 2024Key-Graph Transformer for Image Restorationcited by 3
  11. 2025GraNNite: Enabling High-Performance Execution of Graph Neural Networks on Resource-Constrained Neural Processing Unitscited by 2
  12. 2023Point Cloud Denoising and Outlier Detection with Local Geometric Structure by Dynamic Graph CNNcited by 0
6 more
  1. 2024HGNAS: Hardware-Aware Graph Neural Architecture Search for Edge Devicescited by 0
  2. 2025GCoDE: Efficient Device-Edge Co-Inference for GNNs via Architecture-Mapping Co-Searchcited by 0
  3. 2025Exploring Spatial-Temporal Representation via Star Graph for mmWave Radar-based Human Activity Recognitioncited by 0
  4. 2026HyQuRP: Hybrid quantum-classical neural network with rotational and permutational equivariancecited by 0
  5. 2026Coden: Efficient Temporal Graph Neural Networks for Continuous Predictioncited by 0
  6. 2026Rotation-Invariant Multi-IMU Activity Recognition under Independent Per-Location Orientation Shiftscited by 0