mlsanityData to 14 Oct 2026

CpT: Convolutional Point Transformer for 3D Point Cloud Processing

arXiv 2111.10866 ↗First posted 21 Nov 2021cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

We present CpT: Convolutional point Transformer - a novel deep learning architecture for dealing with the unstructured nature of 3D point cloud data. CpT is an improvement over existing attention-based Convolutions Neural Networks as well as previous 3D point cloud processing transformers. It achieves this feat due to its effectiveness in creating a novel and robust attention-based point set embedding through a convolutional projection layer crafted for processing dynamically local point set neighbourhoods. The resultant point set embedding is robust to the permutations of the input points. Our novel CpT block builds over local neighbourhoods of points obtained via a dynamic graph computation at each layer of the networks' structure. It is fully differentiable and can be stacked just like convolutional layers to learn global properties of the points. We evaluate our model on standard benchmark datasets such as ModelNet40, ShapeNet Part Segmentation, and the S3DIS 3D indoor scene semantic segmentation dataset to show that our model can serve as an effective backbone for various point cloud processing tasks when compared to the existing state-of-the-art approaches.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 39 of its 48 references that are in the map. First posted on arXiv 21 Nov 2021.

Builds on

39 of 48 references.

References · 39

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  6. 2017Squeeze-and-Excitation Networkscited by 4,789
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  8. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  9. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  10. 2020Point Transformercited by 1,470
  11. 2017Deep Setscited by 1,421
  12. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
27 more
  1. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  2. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,026
  3. 2021CvT: Introducing Convolutions to Vision Transformerscited by 947
  4. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  5. 2020PCT: Point cloud transformercited by 732
  6. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  7. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  8. 2019Are Transformers universal approximators of sequence-to-sequence functions?cited by 406
  9. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 385
  10. 2019Axial Attention in Multidimensional Transformerscited by 358
  11. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  12. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  13. 2021SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Trainingcited by 319
  14. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 310
  15. 2021Escaping the Big Data Paradigm with Compact Transformerscited by 264
  16. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  17. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 239
  18. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  19. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  20. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  21. 2018Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networkscited by 122
  22. 2021TABBIE: Pretrained Representations of Tabular Datacited by 111
  23. 2018Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Networkcited by 100
  24. 2018Local Spectral Graph Convolution for Point Set Feature Learningcited by 84
  25. 2019FocusNet: An attention-based Fully Convolutional Network for Medical Image Segmentationcited by 24
  26. 2021FatNet: A Feature-attentive Network for 3D Point Cloud Processingcited by 10
  27. 2019SAWNet: A Spatially Aware Deep Neural Network for 3D Point Cloud Processingcited by 6

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 1; 2025: 4.

8 papers.

  1. 2022The Fully Convolutional Transformer for Medical Image Segmentationcited by 32
  2. 20223D Vision with Transformers: A Surveycited by 21
  3. 2023ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional Attentioncited by 1
  4. 2024Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Trainingcited by 0
  5. 2025Deeply Dual Supervised learning for melanoma recognitioncited by 0
  6. 2025Edge Detection for Organ Boundaries via Top Down Refinement and SubPixel Upsamplingcited by 0
  7. 2025DualResolution Residual Architecture with Artifact Suppression for Melanocytic Lesion Segmentationcited by 0
  8. 2025VesselRW: Weakly Supervised Subcutaneous Vessel Segmentation via Learned Random Walk Propagationcited by 0