mlsanityData to 14 Oct 2026

Point Transformer V2: Grouped Vector Attention and Partition-based Pooling

arXiv 2210.05666 ↗First posted 11 Oct 2022cs.CVcited by 388

Not on the map. Why?

Cited by 21 in State-space sequence models (S4, Mamba), but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

As a pioneering work exploring transformer architecture for 3D point cloud understanding, Point Transformer achieves impressive results on multiple highly competitive benchmarks. In this work, we analyze the limitations of the Point Transformer and propose our powerful and efficient Point Transformer V2 model with novel designs that overcome the limitations of previous work. In particular, we first propose group vector attention, which is more effective than the previous version of vector attention. Inheriting the advantages of both learnable weight encoding and multi-head attention, we present a highly effective implementation of grouped vector attention with a novel grouped weight encoding layer. We also strengthen the position information for attention by an additional position encoding multiplier. Furthermore, we design novel and lightweight partition-based pooling methods which enable better spatial alignment and more efficient sampling. Extensive experiments show that our model achieves better performance than its predecessor and achieves state-of-the-art on several challenging 3D point cloud understanding benchmarks, including 3D point cloud segmentation on ScanNet v2 and S3DIS and 3D point cloud classification on ModelNet40. Our code will be available at https://github.com/Gofinge/PointTransformerV2.

Key facts. Cited by 388 papers in the map (data through 14 Oct 2026). Builds on 44 of its 51 references that are in the map. First posted on arXiv 11 Oct 2022.

Builds on

44 of 51 references.

References · 44

  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. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  7. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  8. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  9. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  10. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  11. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  12. 2020Point Transformercited by 1,470
32 more
  1. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,319
  2. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  3. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  4. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,153
  5. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
  6. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  7. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  8. 2020PCT: Point cloud transformercited by 732
  9. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 724
  10. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  11. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  12. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  13. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 527
  14. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  15. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 385
  16. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  17. 2020Exploring Self-attention for Image Recognitioncited by 313
  18. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 239
  19. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  20. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 179
  21. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  22. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  23. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  24. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  25. 20183DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentationcited by 118
  26. 2016Vehicle Detection from 3D Lidar Using Fully Convolutional Networkcited by 107
  27. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  28. 2019PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Thingscited by 98
  29. 2020A Closer Look at Local Aggregation Operators in Point Cloud Analysiscited by 87
  30. 2019Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentationcited by 68
  31. 2020JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Cloudscited by 62
  32. 2019A Unified Point-Based Framework for 3D Segmentationcited by 34

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 52; 2024: 105; 2025: 138; 2026: 90.

388 papers.

Sort:

By area:

  1. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  2. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 179
  3. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 167
  4. 2023SAM3D: Segment Anything in 3D Scenescited by 157
  5. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  6. 2023Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understandingcited by 113
  7. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 110
  8. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 109
  9. 2023OneFormer3D: One Transformer for Unified Point Cloud Segmentationcited by 95
  10. 2023Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Trainingcited by 86
  11. 2023OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentationcited by 82
  12. 2023FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformercited by 73
38 more
  1. 2023UniPAD: A Universal Pre-training Paradigm for Autonomous Drivingcited by 73
  2. 2024Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategycited by 73
  3. 2024Point Cloud Mamba: Point Cloud Learning via State Space Modelcited by 66
  4. 2025SpatialLM: Training Large Language Models for Structured Indoor Modelingcited by 65
  5. 2022GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Cloudscited by 57
  6. 2024Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Modelcited by 57
  7. 2023Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learningcited by 56
  8. 2023PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigmcited by 56
  9. 2023Towards Label-free Scene Understanding by Vision Foundation Modelscited by 54
  10. 2025SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretrainingcited by 52
  11. 2023FRNet: Frustum-Range Networks for Scalable LiDAR Segmentationcited by 50
  12. 2024Point-SAM: Promptable 3D Segmentation Model for Point Cloudscited by 50
  13. 2023Mask-Attention-Free Transformer for 3D Instance Segmentationcited by 46
  14. 2024TEXGen: a Generative Diffusion Model for Mesh Texturescited by 46
  15. 2025Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representationscited by 45
  16. 2023OmniVec: Learning robust representations with cross modal sharingcited by 44
  17. 2024OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentationcited by 44
  18. 2024Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learningcited by 43
  19. 2024SegPoint: Segment Any Point Cloud via Large Language Modelcited by 35
  20. 2024Find Any Part in 3Dcited by 32
  21. 2025GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Trainingcited by 32
  22. 2025DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentationcited by 31
  23. 2023Scalable, Detailed and Mask-Free Universal Photometric Stereocited by 30
  24. 2024Reason3D: Searching and Reasoning 3D Segmentation via Large Language Modelcited by 28
  25. 2024DN-4DGS: Denoised Deformable Network with Temporal-Spatial Aggregation for Dynamic Scene Renderingcited by 28
  26. 2024TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understandingcited by 27
  27. 2025UAVScenes: A Multi-Modal Dataset for UAVscited by 27
  28. 2024GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understandingcited by 26
  29. 2023Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Modelscited by 25
  30. 2024ODIN: A Single Model for 2D and 3D Segmentationcited by 25
  31. 2024Multi-Space Alignments Towards Universal LiDAR Segmentationcited by 25
  32. 2024DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characterscited by 24
  33. 2023Clustering based Point Cloud Representation Learning for 3D Analysiscited by 23
  34. 2024Any2Point: Empowering Any-modality Large Models for Efficient 3D Understandingcited by 23
  35. 2024RadarPillars: Efficient Object Detection from 4D Radar Point Cloudscited by 23
  36. 2024An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion Modelscited by 23
  37. 2024PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learningcited by 21
  38. 2024ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretrainingcited by 21

50 most cited of 388 All 388 (JSON)