mlsanityData to 7 Oct 2026

Fast Point Transformer

arXiv 2112.04702 ↗First posted 9 Dec 2021cs.CVcited by 103

Not on the map. Why?

Abstract (arXiv)

The recent success of neural networks enables a better interpretation of 3D point clouds, but processing a large-scale 3D scene remains a challenging problem. Most current approaches divide a large-scale scene into small regions and combine the local predictions together. However, this scheme inevitably involves additional stages for pre- and post-processing and may also degrade the final output due to predictions in a local perspective. This paper introduces Fast Point Transformer that consists of a new lightweight self-attention layer. Our approach encodes continuous 3D coordinates, and the voxel hashing-based architecture boosts computational efficiency. The proposed method is demonstrated with 3D semantic segmentation and 3D detection. The accuracy of our approach is competitive to the best voxel-based method, and our network achieves 129 times faster inference time than the state-of-the-art, Point Transformer, with a reasonable accuracy trade-off in 3D semantic segmentation on S3DIS dataset.

Key facts. Cited by 103 papers in the map (data through 7 Oct 2026). Builds on 40 of its 54 references that are in the map. First posted on arXiv 9 Dec 2021.

Builds on

40 of 54 references.

References · 40

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  8. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  9. 2020Point Transformercited by 1,462
  10. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  11. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  12. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
28 more
  1. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  2. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  3. 2020PCT: Point cloud transformercited by 730
  4. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  5. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  6. 2021Transformer in Transformercited by 632
  7. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  8. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  9. 2019Making Convolutional Networks Shift-Invariant Againcited by 390
  10. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  11. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  12. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  13. 2020Exploring Self-attention for Image Recognitioncited by 313
  14. 2021Voxel Transformer for 3D Object Detectioncited by 247
  15. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  16. 2021Scaling Local Self-Attention for Parameter Efficient Visual Backbonescited by 220
  17. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  18. 2019Local Relation Networks for Image Recognitioncited by 210
  19. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 178
  20. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  21. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  22. 2021LambdaNetworks: Modeling Long-Range Interactions Without Attentioncited by 107
  23. 2020Virtual Multi-view Fusion for 3D Semantic Segmentationcited by 99
  24. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  25. 2019Interpolated Convolutional Networks for 3D Point Cloud Understandingcited by 86
  26. 2019LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Latticescited by 38
  27. 2019A Unified Point-Based Framework for 3D Segmentationcited by 33
  28. 2020Torch-Points3D: A Modular Multi-Task Frameworkfor Reproducible Deep Learning on 3D Point Cloudscited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 17; 2023: 34; 2024: 23; 2025: 20; 2026: 9.

103 papers.

Sort:

By area:

  1. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  2. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  3. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 299
  4. 2023Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understandingcited by 111
  5. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 108
  6. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 105
  7. 2023Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Trainingcited by 85
  8. 2023FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformercited by 72
  9. 2022LargeKernel3D: Scaling up Kernels in 3D Sparse CNNscited by 71
  10. 2024Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategycited by 71
  11. 2022GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Cloudscited by 57
  12. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
38 more
  1. 2023Efficient 3D Semantic Segmentation with Superpoint Transformercited by 56
  2. 2023Using a Waffle Iron for Automotive Point Cloud Semantic Segmentationcited by 53
  3. 2023Mask-Attention-Free Transformer for 3D Instance Segmentationcited by 45
  4. 2024OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentationcited by 43
  5. 2023OcTr: Octree-based Transformer for 3D Object Detectioncited by 32
  6. 2022Transformers in 3D Point Clouds: A Surveycited by 31
  7. 2022PointConvFormer: Revenge of the Point-based Convolutioncited by 29
  8. 2022CASSPR: Cross Attention Single Scan Place Recognitioncited by 22
  9. 2022Recent Advances in Vision Transformer: A Survey and Outlook of Recent Workcited by 21
  10. 20223D Vision with Transformers: A Surveycited by 21
  11. 2023PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformercited by 21
  12. 2024PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learningcited by 21
  13. 2024Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentationcited by 20
  14. 2022PeRFception: Perception using Radiance Fieldscited by 19
  15. 2023Point Cloud Classification Using Content-based Transformer via Clustering in Feature Spacecited by 19
  16. 2024Rethinking Few-shot 3D Point Cloud Semantic Segmentationcited by 18
  17. 2025Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Modelcited by 17
  18. 2025LitePT: Lighter Yet Stronger Point Transformercited by 17
  19. 2023ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understandingcited by 16
  20. 2024KPConvX: Modernizing Kernel Point Convolution with Kernel Attentioncited by 16
  21. 2024LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernelscited by 15
  22. 2022Scalable SoftGroup for 3D Instance Segmentation on Point Cloudscited by 14
  23. 2023Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understandingcited by 13
  24. 2023Decoupled Local Aggregation for Point Cloud Learningcited by 12
  25. 2022Bridging Implicit and Explicit Geometric Transformation for Single-Image View Synthesiscited by 11
  26. 2024On permutation-invariant neural networkscited by 10
  27. 2023Radar Instance Transformer: Reliable Moving Instance Segmentation in Sparse Radar Point Cloudscited by 9
  28. 2023Uni3DL: Unified Model for 3D and Language Understandingcited by 9
  29. 2023ViPFormer: Efficient Vision-and-Pointcloud Transformer for Unsupervised Pointcloud Understandingcited by 8
  30. 2023EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localizationcited by 8
  31. 2023PointWavelet: Learning in Spectral Domain for 3D Point Cloud Analysiscited by 7
  32. 2024Dynamic 3D Point Cloud Sequences as 2D Videoscited by 7
  33. 2024ARKit LabelMaker: A New Scale for Indoor 3D Scene Understandingcited by 7
  34. 2023Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentationcited by 6
  35. 2024Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene Understandingcited by 6
  36. 2025Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Fieldcited by 6
  37. 2023Full Point Encoding for Local Feature Aggregation in 3D Point Cloudscited by 5
  38. 2023Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentationcited by 5

50 most cited of 103 All 103 (JSON)