mlsanityData to 14 Oct 2026

Deep Parametric Continuous Convolutional Neural Networks

arXiv 2101.06742 ↗First posted 17 Jan 2021cs.CV cs.AI cs.LGcited by 161

Not on the map. Why?

Abstract (arXiv)

Standard convolutional neural networks assume a grid structured input is available and exploit discrete convolutions as their fundamental building blocks. This limits their applicability to many real-world applications. In this paper we propose Parametric Continuous Convolution, a new learnable operator that operates over non-grid structured data. The key idea is to exploit parameterized kernel functions that span the full continuous vector space. This generalization allows us to learn over arbitrary data structures as long as their support relationship is computable. Our experiments show significant improvement over the state-of-the-art in point cloud segmentation of indoor and outdoor scenes, and lidar motion estimation of driving scenes.

Key facts. Cited by 161 papers in the map (data through 14 Oct 2026). Builds on 23 of its 32 references that are in the map. First posted on arXiv 17 Jan 2021.

Builds on

23 of 32 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  8. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
  9. 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
  10. 2015Gated Graph Sequence Neural Networkscited by 796
  11. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
  12. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 571
11 more
  1. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  2. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  3. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 342
  4. 2016Dynamic Filter Networkscited by 319
  5. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 310
  6. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  7. 2017Submanifold Sparse Convolutional Networkscited by 223
  8. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 179
  9. 2014Learning Rich Features from RGB-D Images for Object Detection and Segmentationcited by 127
  10. 2016Learning shape correspondence with anisotropic convolutional neural networkscited by 95
  11. 2016SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentationcited by 70

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 49; 2022: 47; 2023: 31; 2024: 21; 2025: 8; 2026: 5.

161 papers.

Sort:

By area:

  1. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  2. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  3. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 388
  4. 2023Convolutional Neural Operators for robust and accurate learning of PDEscited by 214
  5. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  6. 2022Towards Multi-spatiotemporal-scale Generalized PDE Modelingcited by 197
  7. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 167
  8. 2021InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referringcited by 141
  9. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  10. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  11. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  12. 2021CKConv: Continuous Kernel Convolution For Sequential Datacited by 120
38 more
  1. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 110
  2. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  3. 2022Learning to Generate Realistic LiDAR Point Cloudscited by 93
  4. 2022POCO: Point Convolution for Surface Reconstructioncited by 92
  5. 2023Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Trainingcited by 86
  6. 2022Surface Representation for Point Cloudscited by 84
  7. 2021PointMixer: MLP-Mixer for Point Cloud Understandingcited by 71
  8. 2021FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizescited by 66
  9. 2021Multi-Modal 3D Object Detection in Autonomous Driving: a Surveycited by 63
  10. 2024Neural Operators with Localized Integral and Differential Kernelscited by 62
  11. 2021Weakly Supervised Learning of Rigid 3D Scene Flowcited by 60
  12. 2021Adaptive Graph Convolution for Point Cloud Analysiscited by 60
  13. 2021PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysiscited by 58
  14. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  15. 2021Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Cloudscited by 55
  16. 2021Learning Semantic Segmentation of Large-Scale Point Clouds with Random Samplingcited by 51
  17. 2021Scalable Scene Flow from Point Clouds in the Real Worldcited by 50
  18. 2024Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applicationscited by 50
  19. 2021Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentationcited by 40
  20. 2022Meta Architecture for Point Cloud Analysiscited by 40
  21. 2023Self-positioning Point-based Transformer for Point Cloud Understandingcited by 40
  22. 2021Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walkcited by 39
  23. 2023Smooth, exact rotational symmetrization for deep learning on point cloudscited by 39
  24. 2021HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embeddingcited by 36
  25. 2022Deep Depth Completion from Extremely Sparse Data: A Surveycited by 33
  26. 2021Deep Learning Based 3D Segmentation: A Surveycited by 30
  27. 2022PointConvFormer: Revenge of the Point-based Convolutioncited by 30
  28. 2021Learning Inner-Group Relations on Point Cloudscited by 29
  29. 2021ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learningcited by 29
  30. 2021LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignmentcited by 26
  31. 2021Roto-translated Local Coordinate Frames For Interacting Dynamical Systemscited by 24
  32. 2022A Closer Look at Invariances in Self-supervised Pre-training for 3D Visioncited by 24
  33. 2024Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpaintingcited by 24
  34. 20213D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysiscited by 23
  35. 2022Refine-Net: Normal Refinement Neural Network for Noisy Point Cloudscited by 23
  36. 2023Clustering based Point Cloud Representation Learning for 3D Analysiscited by 23
  37. 2021Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfercited by 20
  38. 2023Modelling Long Range Dependencies in ND: From Task-Specific to a General Purpose CNNcited by 18

50 most cited of 161 All 161 (JSON)