mlsanityData to 7 Oct 2026

Stratified Transformer for 3D Point Cloud Segmentation

arXiv 2203.14508 ↗First posted 28 Mar 2022cs.CV cs.AIcited by 166

Not on the map. Why?

Abstract (arXiv)

3D point cloud segmentation has made tremendous progress in recent years. Most current methods focus on aggregating local features, but fail to directly model long-range dependencies. In this paper, we propose Stratified Transformer that is able to capture long-range contexts and demonstrates strong generalization ability and high performance. Specifically, we first put forward a novel key sampling strategy. For each query point, we sample nearby points densely and distant points sparsely as its keys in a stratified way, which enables the model to enlarge the effective receptive field and enjoy long-range contexts at a low computational cost. Also, to combat the challenges posed by irregular point arrangements, we propose first-layer point embedding to aggregate local information, which facilitates convergence and boosts performance. Besides, we adopt contextual relative position encoding to adaptively capture position information. Finally, a memory-efficient implementation is introduced to overcome the issue of varying point numbers in each window. Extensive experiments demonstrate the effectiveness and superiority of our method on S3DIS, ScanNetv2 and ShapeNetPart datasets. Code is available at https://github.com/dvlab-research/Stratified-Transformer.

Key facts. Cited by 166 papers in the map (data through 7 Oct 2026). Builds on 57 of its 62 references that are in the map. First posted on arXiv 28 Mar 2022.

Builds on

57 of 62 references.

References · 57

  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. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2016Layer Normalizationcited by 5,579
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  8. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  9. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  10. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  11. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  12. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
38 more
  1. 2017Non-local Neural Networkscited by 2,290
  2. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  3. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  4. 2020Point Transformercited by 1,462
  5. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  6. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  7. 2020On Layer Normalization in the Transformer Architecturecited by 906
  8. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  9. 2021Going deeper with Image Transformerscited by 759
  10. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
  11. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  12. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  13. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  14. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  15. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
  16. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  17. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  18. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  19. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  20. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  21. 2020Exploring Self-attention for Image Recognitioncited by 313
  22. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 286
  23. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  24. 2021Voxel Transformer for 3D Object Detectioncited by 247
  25. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  26. 2017Submanifold Sparse Convolutional Networkscited by 223
  27. 2021Group-Free 3D Object Detection via Transformerscited by 215
  28. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  29. 2021Rethinking and Improving Relative Position Encoding for Vision Transformercited by 206
  30. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 178
  31. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  32. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  33. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  34. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  35. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  36. 20183DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentationcited by 118
  37. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  38. 2018Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Networkcited by 100

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 20; 2023: 66; 2024: 35; 2025: 25; 2026: 20.

166 papers.

Sort:

By area:

  1. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  2. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 299
  3. 2022Motion Transformer with Global Intention Localization and Local Movement Refinementcited by 267
  4. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  5. 2022PLA: Language-Driven Open-Vocabulary 3D Scene Understandingcited by 176
  6. 2023MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Queryingcited by 139
  7. 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 124
  8. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  9. 2023Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understandingcited by 111
  10. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 105
  11. 2023RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understandingcited by 93
  12. 2023Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Trainingcited by 85
38 more
  1. 2022LargeKernel3D: Scaling up Kernels in 3D Sparse CNNscited by 71
  2. 2024Point Cloud Mamba: Point Cloud Learning via State Space Modelcited by 66
  3. 2022GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Cloudscited by 57
  4. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  5. 2023Efficient 3D Semantic Segmentation with Superpoint Transformercited by 56
  6. 2023PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigmcited by 56
  7. 2023Using a Waffle Iron for Automotive Point Cloud Semantic Segmentationcited by 53
  8. 2023Understanding Imbalanced Semantic Segmentation Through Neural Collapsecited by 46
  9. 2023Mask-Attention-Free Transformer for 3D Instance Segmentationcited by 45
  10. 2022Meta Architecture for Point Cloud Analysiscited by 39
  11. 2023Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understandingcited by 38
  12. 2023Attention-based Point Cloud Edge Samplingcited by 37
  13. 2023Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysiscited by 34
  14. 2023V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detectioncited by 34
  15. 2024RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radarcited by 32
  16. 2022Transformers in 3D Point Clouds: A Surveycited by 31
  17. 2022PointConvFormer: Revenge of the Point-based Convolutioncited by 29
  18. 2024SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decompositioncited by 29
  19. 2023Prototype Adaption and Projection for Few- and Zero-shot 3D Point Cloud Semantic Segmentationcited by 26
  20. 2023Building3D: An Urban-Scale Dataset and Benchmarks for Learning Roof Structures from Point Cloudscited by 24
  21. 2023Advancements in Point Cloud Data Augmentation for Deep Learning: A Surveycited by 24
  22. 2023Clustering based Point Cloud Representation Learning for 3D Analysiscited by 23
  23. 2024RadarPillars: Efficient Object Detection from 4D Radar Point Cloudscited by 23
  24. 2023Adaptive Spot-Guided Transformer for Consistent Local Feature Matchingcited by 22
  25. 2022PointVector: A Vector Representation In Point Cloud Analysiscited by 21
  26. 20223D Vision with Transformers: A Surveycited by 21
  27. 2023PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformercited by 21
  28. 2023Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 21
  29. 2024Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentationcited by 20
  30. 2023Point Cloud Classification Using Content-based Transformer via Clustering in Feature Spacecited by 19
  31. 2023Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancementcited by 19
  32. 2023Benchmarking the Robustness of LiDAR Semantic Segmentation Modelscited by 18
  33. 2023HEAL-SWIN: A Vision Transformer On The Spherecited by 18
  34. 2023ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understandingcited by 16
  35. 2022Gaussian Radar Transformer for Semantic Segmentation in Noisy Radar Datacited by 15
  36. 2024A Unified Framework for 3D Scene Understandingcited by 15
  37. 20233DTeethSeg'22: 3D Teeth Scan Segmentation and Labeling Challengecited by 14
  38. 2023Computation-efficient Deep Learning for Computer Vision: A Surveycited by 14

50 most cited of 166 All 166 (JSON)