mlsanityData to 7 Oct 2026

Efficient 3D Semantic Segmentation with Superpoint Transformer

arXiv 2306.08045 ↗First posted 13 Jun 2023cs.CVcited by 56

Not on the map. Why?

Abstract (arXiv)

We introduce a novel superpoint-based transformer architecture for efficient semantic segmentation of large-scale 3D scenes. Our method incorporates a fast algorithm to partition point clouds into a hierarchical superpoint structure, which makes our preprocessing 7 times faster than existing superpoint-based approaches. Additionally, we leverage a self-attention mechanism to capture the relationships between superpoints at multiple scales, leading to state-of-the-art performance on three challenging benchmark datasets: S3DIS (76.0% mIoU 6-fold validation), KITTI-360 (63.5% on Val), and DALES (79.6%). With only 212k parameters, our approach is up to 200 times more compact than other state-of-the-art models while maintaining similar performance. Furthermore, our model can be trained on a single GPU in 3 hours for a fold of the S3DIS dataset, which is 7x to 70x fewer GPU-hours than the best-performing methods. Our code and models are accessible at github.com/drprojects/superpoint_transformer.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Builds on 41 of its 63 references that are in the map. First posted on arXiv 13 Jun 2023.

Builds on

41 of 63 references.

References · 41

  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. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2017Graph Attention Networkscited by 8,854
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  8. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  9. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  10. 2020Point Transformercited by 1,462
  11. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  12. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
29 more
  1. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  2. 2020PCT: Point cloud transformercited by 730
  3. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  4. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  5. 2019Graph U-Netscited by 489
  6. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  7. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  8. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  9. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  10. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  11. 2020OccuSeg: Occupancy-aware 3D Instance Segmentationcited by 177
  12. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 166
  13. 20203D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentationcited by 140
  14. 2021Hierarchical Aggregation for 3D Instance Segmentationcited by 126
  15. 2020GraphNorm: A Principled Approach to Accelerating Graph Neural Network Trainingcited by 116
  16. 2021Fast Point Transformercited by 103
  17. 2021Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networkscited by 98
  18. 2021Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understandingcited by 97
  19. 2022Surface Representation for Point Cloudscited by 84
  20. 2020DALES: A Large-scale Aerial LiDAR Data Set for Semantic Segmentationcited by 65
  21. 2019ConvPoint: Continuous Convolutions for Point Cloud Processingcited by 62
  22. 2022Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentationcited by 47
  23. 2019Point Cloud Oversegmentation with Graph-Structured Deep Metric Learningcited by 42
  24. 2020Torch-Points3D: A Modular Multi-Task Frameworkfor Reproducible Deep Learning on 3D Point Cloudscited by 23
  25. 2022Online Segmentation of LiDAR Sequences: Dataset and Algorithmcited by 14
  26. 2023Region-Enhanced Feature Learning for Scene Semantic Segmentationcited by 6
  27. 2022Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densitiescited by 5
  28. 2019Parallel Cut Pursuit For Minimization of the Graph Total Variationcited by 4
  29. 2016Hierarchical image simplification and segmentation based on Mumford-Shah-salient level line selectioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 13; 2025: 27; 2026: 12.

56 papers.

Sort:

By area:

  1. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  2. 2023Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidancecited by 123
  3. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 108
  4. 2024Point Cloud Mamba: Point Cloud Learning via State Space Modelcited by 66
  5. 2025Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registrationcited by 50
  6. 20233D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentationcited by 36
  7. 2023SAM-guided Graph Cut for 3D Instance Segmentationcited by 35
  8. 2024SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussianscited by 30
  9. 2025LitePT: Lighter Yet Stronger Point Transformercited by 17
  10. 2024Scalable 3D Panoptic Segmentation As Superpoint Graph Clusteringcited by 14
  11. 2024ECLAIR: A High-Fidelity Aerial LiDAR Dataset for Semantic Segmentationcited by 10
  12. 2024PureForest: A Large-Scale Aerial Lidar and Aerial Imagery Dataset for Tree Species Classification in Monospecific Forestscited by 9
38 more
  1. 2025LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Cloudscited by 8
  2. 2025COS3D: Collaborative Open-Vocabulary 3D Segmentationcited by 8
  3. 2025Unsupervised deep learning for semantic segmentation of multispectral LiDAR forest point cloudscited by 7
  4. 2024Unsupervised semantic segmentation of urban high-density multispectral point cloudscited by 4
  5. 2024OE3DIS: Open-Ended 3D Point Cloud Instance Segmentationcited by 3
  6. 2024Beyond Grid Data: Exploring Graph Neural Networks for Earth Observationcited by 3
  7. 2025CloudMamba: Grouped Selective State Spaces for Point Cloud Analysiscited by 3
  8. 20253DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentationcited by 2
  9. 2025HydraMamba: Multi-Head State Space Model for Global Point Cloud Learningcited by 2
  10. 2025SGS-3D: High-Fidelity 3D Instance Segmentation via Reliable Semantic Mask Splitting and Growingcited by 2
  11. 2025TrueCity: Real and Simulated Urban Data for Cross-Domain 3D Scene Understandingcited by 2
  12. 20243D Learnable Supertoken Transformer for LiDAR Point Cloud Scene Segmentationcited by 1
  13. 2024Exploring contextual modeling with linear complexity for point cloud segmentationcited by 1
  14. 2025CHaRM: Conditioned Heatmap Regression Methodology for Accurate and Fast Dental Landmark Localizationcited by 1
  15. 2025Cross-modal feature fusion for robust point cloud registration with ambiguous geometrycited by 1
  16. 2025HyperPointFormer: Multimodal Fusion in 3D Space with Dual-Branch Cross-Attention Transformerscited by 1
  17. 2025SPPSFormer: High-quality Superpoint-based Transformer for Roof Plane Instance Segmentation from Point Cloudscited by 1
  18. 2025PointGS: Point Attention-Aware Sparse View Synthesis with Gaussian Splattingcited by 1
  19. 2025HARP-NeXt: High-Speed and Accurate Range-Point Fusion Network for 3D LiDAR Semantic Segmentationcited by 1
  20. 2025Foundry: Distilling 3D Foundation Models for the Edgecited by 1
  21. 2025EZ-SP: Fast and Lightweight Superpoint-Based 3D Segmentationcited by 1
  22. 2026Efficient Encoder-Free Fourier-based 3D Large Multimodal Modelcited by 1
  23. 2026RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodingscited by 1
  24. 2026UnderOneFacade: Worldwide Facade Semantic Segmentation Benchmark Datasetcited by 1
  25. 2024Efficient Point Transformer with Dynamic Token Aggregating for LiDAR Point Cloud Processingcited by 0
  26. 2024Fine-grained Metrics for Point Cloud Semantic Segmentationcited by 0
  27. 2024Density-aware global-local attention network for point cloud segmentationcited by 0
  28. 2025HAECcity: Open-Vocabulary Scene Understanding of City-Scale Point Clouds with Superpoint Graph Clusteringcited by 0
  29. 2025NVSMask3D: Hard Visual Prompting with Camera Pose Interpolation for 3D Open Vocabulary Instance Segmentationcited by 0
  30. 2025Towards Generalized Range-View LiDAR Segmentation in Adverse Weathercited by 0
  31. 2025MR-COSMO: Visual-Text Memory Recall and Direct CrOSs-MOdal Alignment Method for Query-Driven 3D Segmentationcited by 0
  32. 2025Multispectral LiDAR data for extracting tree points in urban and suburban areascited by 0
  33. 2025Point-level Uncertainty Evaluation of Mobile Laser Scanning Point Cloudscited by 0
  34. 2025From Propagation to Prediction: Point-level Uncertainty Evaluation of MLS Point Clouds under Limited Ground Truthcited by 0
  35. 2026GridNet-HD: A High-Resolution Multi-Modal Dataset for LiDAR-Image Fusion on Power Line Infrastructurecited by 0
  36. 2025COSMOS: Coherent Supergaussian Modeling with Spatial Priors for Sparse-View 3D Splattingcited by 0
  37. 2026Benchmarking Deep Learning Models for Aerial LiDAR Point Cloud Semantic Segmentation under Real Acquisition Conditions: A Case Study in Navarrecited by 0
  38. 2026Spatially-Aware Evaluation Framework for Aerial LiDAR Point Cloud Semantic Segmentation: Distance-Based Metrics on Challenging Regionscited by 0

50 most cited of 56 All 56 (JSON)