mlsanityData to 7 Oct 2026

SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds

arXiv 2104.04891 ↗First posted 11 Apr 2021cs.CV cs.AI cs.ROcited by 64

Not on the map. Why?

Abstract (arXiv)

Labelling point clouds fully is highly time-consuming and costly. As larger point cloud datasets with billions of points become more common, we ask whether the full annotation is even necessary, demonstrating that existing baselines designed under a fully annotated assumption only degrade slightly even when faced with 1% random point annotations. However, beyond this point, e.g., at 0.1% annotations, segmentation accuracy is unacceptably low. We observe that, as point clouds are samples of the 3D world, the distribution of points in a local neighborhood is relatively homogeneous, exhibiting strong semantic similarity. Motivated by this, we propose a new weak supervision method to implicitly augment highly sparse supervision signals. Extensive experiments demonstrate the proposed Semantic Query Network (SQN) achieves promising performance on seven large-scale open datasets under weak supervision schemes, while requiring only 0.1% randomly annotated points for training, greatly reducing annotation cost and effort. The code is available at https://github.com/QingyongHu/SQN.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). Builds on 65 of its 108 references that are in the map. First posted on arXiv 11 Apr 2021.

Builds on

65 of 108 references.

References · 65

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  8. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  9. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  10. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  11. 2020Point Transformercited by 1,462
  12. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
38 more
  1. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  2. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  3. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  4. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  5. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  6. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  7. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  8. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  9. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  10. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  11. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
  12. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  13. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  14. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  15. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  16. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  17. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 231
  18. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  19. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 222
  20. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  21. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  22. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 178
  23. 2020OccuSeg: Occupancy-aware 3D Instance Segmentationcited by 177
  24. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  25. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  26. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  27. 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
  28. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  29. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  30. 2020Virtual Multi-view Fusion for 3D Semantic Segmentationcited by 99
  31. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  32. 2018Recurrent Slice Networks for 3D Segmentation of Point Cloudscited by 82
  33. 2020Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challengescited by 80
  34. 2020Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadwayscited by 77
  35. 2019Multi-view PointNet for 3D Scene Understandingcited by 76
  36. 2020Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Cloudscited by 71
  37. 2020Self-Supervised Few-Shot Learning on Point Cloudscited by 66
  38. 2017Paris-Lille-3D: a large and high-quality ground truth urban point cloud dataset for automatic segmentation and classificationcited by 65

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 17; 2023: 17; 2024: 14; 2025: 12; 2026: 2.

64 papers.

Sort:

By area:

  1. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  2. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 123
  3. 2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 92
  4. 2024Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Drivingcited by 53
  5. 2022STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Datasetcited by 52
  6. 2022LESS: Label-Efficient Semantic Segmentation for LiDAR Point Cloudscited by 41
  7. 2023GrowSP: Unsupervised Semantic Segmentation of 3D Point Cloudscited by 34
  8. 20244D Contrastive Superflows are Dense 3D Representation Learnerscited by 32
  9. 2022No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfacescited by 25
  10. 2023Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 21
  11. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  12. 2021Superpoint-guided Semi-supervised Semantic Segmentation of 3D Point Cloudscited by 19
38 more
  1. 2022Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoningcited by 16
  2. 2022LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentationcited by 16
  3. 20232D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervisioncited by 16
  4. 2022Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentationcited by 15
  5. 2022Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learningcited by 15
  6. 2022COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentationcited by 15
  7. 2023PointDC:Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-modal Distillation and Super-Voxel Clusteringcited by 15
  8. 2024Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 15
  9. 2022Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learningcited by 13
  10. 2023All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentationcited by 13
  11. 2021A new weakly supervised approach for ALS point cloud semantic segmentationcited by 12
  12. 2023CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentationcited by 12
  13. 20243D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidancecited by 12
  14. 2022Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervisioncited by 11
  15. 2023Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentationcited by 11
  16. 2025LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Drivingcited by 11
  17. 2025LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Cloudscited by 8
  18. 2022PointMatch: A Consistency Training Framework for Weakly Supervised Semantic Segmentation of 3D Point Cloudscited by 7
  19. 2023ClickSeg: 3D Instance Segmentation with Click-Level Weak Annotationscited by 7
  20. 2025Unsupervised deep learning for semantic segmentation of multispectral LiDAR forest point cloudscited by 7
  21. 2022Meta-Sampler: Almost-Universal yet Task-Oriented Sampling for Point Cloudscited by 6
  22. 2024Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimizationcited by 6
  23. 2022One Class One Click: Quasi Scene-level Weakly Supervised Point Cloud Semantic Segmentation with Active Learningcited by 5
  24. 2023Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentationcited by 5
  25. 2023MWSIS: Multimodal Weakly Supervised Instance Segmentation with 2D Box Annotations for Autonomous Drivingcited by 5
  26. 2024Enhancing Diffusion-based Point Cloud Generation with Smoothness Constraintcited by 5
  27. 2024When 3D Partial Points Meets SAM: Tooth Point Cloud Segmentation with Sparse Labelscited by 5
  28. 2024Multi-modal NeRF Self-Supervision for LiDAR Semantic Segmentationcited by 5
  29. 2025LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectivescited by 4
  30. 2025Enhanced Spatiotemporal Consistency for Image-to-LiDAR Data Pretrainingcited by 4
  31. 2023Small but Mighty: Enhancing 3D Point Clouds Semantic Segmentation with U-Next Frameworkcited by 3
  32. 2024PointMT: Efficient Point Cloud Analysis with Hybrid MLP-Transformer Architecturecited by 3
  33. 2024Weakly Supervised LiDAR Semantic Segmentation via Scatter Image Annotationcited by 2
  34. 2024Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentationcited by 2
  35. 2022Hypergraph Convolutional Network based Weakly Supervised Point Cloud Semantic Segmentation with Scene-Level Annotationscited by 1
  36. 2023PVP: Pre-trained Visual Parameter-Efficient Tuningcited by 1
  37. 2023Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignmentcited by 1
  38. 2024Towards Modality-agnostic Label-efficient Segmentation with Entropy-Regularized Distribution Alignmentcited by 1

50 most cited of 64 All 64 (JSON)