mlsanityData to 7 Oct 2026

APPT : Asymmetric Parallel Point Transformer for 3D Point Cloud Understanding

arXiv 2303.17815 ↗First posted 31 Mar 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Transformer-based networks have achieved impressive performance in 3D point cloud understanding. However, most of them concentrate on aggregating local features, but neglect to directly model global dependencies, which results in a limited effective receptive field. Besides, how to effectively incorporate local and global components also remains challenging. To tackle these problems, we propose Asymmetric Parallel Point Transformer (APPT). Specifically, we introduce Global Pivot Attention to extract global features and enlarge the effective receptive field. Moreover, we design the Asymmetric Parallel structure to effectively integrate local and global information. Combined with these designs, APPT is able to capture features globally throughout the entire network while focusing on local-detailed features. Extensive experiments show that our method outperforms the priors and achieves state-of-the-art on several benchmarks for 3D point cloud understanding, such as 3D semantic segmentation on S3DIS, 3D shape classification on ModelNet40, and 3D part segmentation on ShapeNet.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 54 of its 62 references that are in the map. First posted on arXiv 31 Mar 2023.

Builds on

54 of 62 references.

References · 54

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2017Squeeze-and-Excitation Networkscited by 4,763
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2020Point Transformercited by 1,462
  10. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  11. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  12. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
38 more
  1. 2021Multiscale Vision Transformerscited by 896
  2. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  3. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  4. 2020PCT: Point cloud transformercited by 730
  5. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 671
  6. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  7. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  8. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
  9. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  10. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  11. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  12. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  13. 2022Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizationscited by 359
  14. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  15. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  16. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  17. 2022How Do Vision Transformers Work?cited by 305
  18. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  19. 2021Voxel Transformer for 3D Object Detectioncited by 247
  20. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  21. 2019High-Resolution Representations for Labeling Pixels and Regionscited by 211
  22. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  23. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 166
  24. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  25. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  26. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  27. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  28. 2021TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?cited by 127
  29. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  30. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  31. 2021Fast Point Transformercited by 103
  32. 2018Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Networkcited by 100
  33. 2022Inception Transformercited by 99
  34. 2021Shunted Self-Attention via Multi-Scale Token Aggregationcited by 90
  35. 2019Interpolated Convolutional Networks for 3D Point Cloud Understandingcited by 86
  36. 2022Surface Representation for Point Cloudscited by 84
  37. 2018Recurrent Slice Networks for 3D Segmentation of Point Cloudscited by 82
  38. 2021PointMixer: MLP-Mixer for Point Cloud Understandingcited by 71

50 most cited of 54 All 54 (JSON)

Built on by

Not cited yet.