mlsanityData to 7 Oct 2026

PointCAT: Cross-Attention Transformer for point cloud

arXiv 2304.03012 ↗First posted 6 Apr 2023cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Transformer-based models have significantly advanced natural language processing and computer vision in recent years. However, due to the irregular and disordered structure of point cloud data, transformer-based models for 3D deep learning are still in their infancy compared to other methods. In this paper we present Point Cross-Attention Transformer (PointCAT), a novel end-to-end network architecture using cross-attentions mechanism for point cloud representing. Our approach combines multi-scale features via two seprate cross-attention transformer branches. To reduce the computational increase brought by multi-branch structure, we further introduce an efficient model for shape classification, which only process single class token of one branch as a query to calculate attention map with the other. Extensive experiments demonstrate that our method outperforms or achieves comparable performance to several approaches in shape classification, part segmentation and semantic segmentation tasks.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 47 of its 57 references that are in the map. First posted on arXiv 6 Apr 2023.

Builds on

47 of 57 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  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. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  9. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  10. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  11. 2020Point Transformercited by 1,462
  12. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
35 more
  1. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  2. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  3. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  4. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  5. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  6. 2020PCT: Point cloud transformercited by 730
  7. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  8. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  9. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  10. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  11. 2019Attention Augmented Convolutional Networkscited by 363
  12. 2021Rethinking Spatial Dimensions of Vision Transformerscited by 361
  13. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  14. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  15. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  16. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  17. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  18. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  19. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  20. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  21. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 178
  22. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  23. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  24. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  25. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  26. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  27. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  28. 2016Generative and Discriminative Voxel Modeling with Convolutional Neural Networkscited by 128
  29. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  30. 2018Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Networkcited by 100
  31. 2019Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentationcited by 68
  32. 2020FPConv: Learning Local Flattening for Point Convolutioncited by 55
  33. 2018A Graph-CNN for 3D Point Cloud Classificationcited by 49
  34. 2021Learning Inner-Group Relations on Point Cloudscited by 29
  35. 2021Styleformer: Transformer based Generative Adversarial Networks with Style Vectorcited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024CTRL-F: Pairing Convolution with Transformer for Image Classification via Multi-Level Feature Cross-Attention and Representation Learning Fusioncited by 1
  2. 2026PCT-Prompt: A Prompt-Guided Transformer Framework for Dense Prediction Tasks in Point Cloudscited by 0