mlsanityData to 7 Oct 2026

GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds

arXiv 2305.16404 ↗First posted 25 May 2023cs.CV cs.AI cs.LGcited by 34

Not on the map. Why?

Abstract (arXiv)

We study the problem of 3D semantic segmentation from raw point clouds. Unlike existing methods which primarily rely on a large amount of human annotations for training neural networks, we propose the first purely unsupervised method, called GrowSP, to successfully identify complex semantic classes for every point in 3D scenes, without needing any type of human labels or pretrained models. The key to our approach is to discover 3D semantic elements via progressive growing of superpoints. Our method consists of three major components, 1) the feature extractor to learn per-point features from input point clouds, 2) the superpoint constructor to progressively grow the sizes of superpoints, and 3) the semantic primitive clustering module to group superpoints into semantic elements for the final semantic segmentation. We extensively evaluate our method on multiple datasets, demonstrating superior performance over all unsupervised baselines and approaching the classic fully-supervised PointNet. We hope our work could inspire more advanced methods for unsupervised 3D semantic learning.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 62 of its 81 references that are in the map. First posted on arXiv 25 May 2023.

Builds on

62 of 81 references.

References · 62

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  7. 2020Point Transformercited by 1,462
  8. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  9. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  10. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  11. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  12. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
38 more
  1. 2020PCT: Point cloud transformercited by 730
  2. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  3. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  4. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  5. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  6. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  7. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  8. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 454
  9. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
  10. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  11. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  12. 2022Language-Grounded Indoor 3D Semantic Segmentation in the Wildcited by 243
  13. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 231
  14. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  15. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  16. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  17. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  18. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  19. 2021PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clusteringcited by 163
  20. 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
  21. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 157
  22. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  23. 2021Capturing, Reconstructing, and Simulating: the UrbanScene3D Datasetcited by 117
  24. 2020Virtual Multi-view Fusion for 3D Semantic Segmentationcited by 99
  25. 2022Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Modelscited by 95
  26. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  27. 2020Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challengescited by 80
  28. 2020Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadwayscited by 77
  29. 2022MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentationcited by 76
  30. 2020Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Cloudscited by 75
  31. 2020Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Cloudscited by 71
  32. 2022Scribble-Supervised LiDAR Semantic Segmentationcited by 69
  33. 2020DALES: A Large-scale Aerial LiDAR Data Set for Semantic Segmentationcited by 65
  34. 2018VV-Net: Voxel VAE Net with Group Convolutions for Point Cloud Segmentationcited by 64
  35. 2021SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Cloudscited by 64
  36. 2020Autoregressive Unsupervised Image Segmentationcited by 60
  37. 2021EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentationcited by 59
  38. 2021ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentationcited by 52

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 12; 2025: 8; 2026: 7.

34 papers.

Sort:

By area:

  1. 2023SAI3D: Segment Any Instance in 3D Scenescited by 90
  2. 2024Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understandingcited by 46
  3. 20244D Contrastive Superflows are Dense 3D Representation Learnerscited by 32
  4. 2024Multi-Space Alignments Towards Universal LiDAR Segmentationcited by 24
  5. 2023ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentationcited by 18
  6. 2023U3DS3: Unsupervised 3D Semantic Scene Segmentationcited by 16
  7. 2024Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 15
  8. 2024Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Surveycited by 12
  9. 2024Part2Object: Hierarchical Unsupervised 3D Instance Segmentationcited by 12
  10. 2024PointSeg: A Training-Free Paradigm for 3D Scene Segmentation via Foundation Modelscited by 9
  11. 2024Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud Segmentationcited by 9
  12. 2024Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perceptioncited by 8
22 more
  1. 2025LeAP: Consistent multi-domain 3D labeling using Foundation Modelscited by 8
  2. 2025LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Cloudscited by 8
  3. 2023A Survey on Trustworthy Edge Intelligence: From Security and Reliability To Transparency and Sustainabilitycited by 7
  4. 2024Unsupervised semantic segmentation of urban high-density multispectral point cloudscited by 4
  5. 2024Refining Segmentation On-the-Fly: An Interactive Framework for Point Cloud Semantic Segmentationcited by 3
  6. 2023LiDAR-BEVMTN: Real-Time LiDAR Bird's-Eye View Multi-Task Perception Network for Autonomous Drivingcited by 2
  7. 2024HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenescited by 2
  8. 2025Aligning Instance-Semantic Sparse Representation towards Unsupervised Object Segmentation and Shape Abstraction with Repeatable Primitivescited by 2
  9. 2025DiSCO-3D : Discovering and segmenting Sub-Concepts from Open-vocabulary queries in NeRFcited by 2
  10. 2023Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignmentcited by 1
  11. 2025Label-Efficient LiDAR Panoptic Segmentationcited by 1
  12. 20253D Weakly Supervised Semantic Segmentation via Class-Aware and Geometry-Guided Pseudo-Label Refinementcited by 1
  13. 2025Late-decoupled 3D Hierarchical Semantic Segmentation with Semantic Prototype Discrimination based Bi-branch Supervisioncited by 1
  14. 2025EZ-SP: Fast and Lightweight Superpoint-Based 3D Segmentationcited by 1
  15. 2026PointGS: Semantic-Consistent Unsupervised 3D Point Cloud Segmentation with 3D Gaussian Splattingcited by 1
  16. 2023Weakly Supervised Point Cloud Segmentation via Conservative Propagation of Scene-level Labelscited by 0
  17. 2026Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentationcited by 0
  18. 2026UniGround: Universal 3D Visual Grounding via Training-Free Scene Parsingcited by 0
  19. 2026Distill, Diffuse, Segment: Unsupervised 3D Semantic Segmentation for Autonomous Driving Based on Multi-Level Distillation and Graph Diffusioncited by 0
  20. 2026Resolving Long-Tail Ambiguity in Unsupervised 3D Point Cloud Segmentation with Language Priorscited by 0
  21. 2026GVC-Seg: Training-Free 3D Instance Segmentation via Geometric Visual Correspondencecited by 0
  22. 2026MSSP: Multi-Scale Spatially-Constrained Partition for Unsupervised Semantic Segmentation of 3D Point Cloudscited by 0