mlsanityData to 7 Oct 2026

PointMatch: A Consistency Training Framework for Weakly Supervised Semantic Segmentation of 3D Point Clouds

arXiv 2202.10705 ↗First posted 22 Feb 2022cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Semantic segmentation of point cloud usually relies on dense annotation that is exhausting and costly, so it attracts wide attention to investigate solutions for the weakly supervised scheme with only sparse points annotated. Existing works start from the given labels and propagate them to highly-related but unlabeled points, with the guidance of data, e.g. intra-point relation. However, it suffers from (i) the inefficient exploitation of data information, and (ii) the strong reliance on labels thus is easily suppressed when given much fewer annotations. Therefore, we propose a novel framework, PointMatch, that stands on both data and label, by applying consistency regularization to sufficiently probe information from data itself and leveraging weak labels as assistance at the same time. By doing so, meaningful information can be learned from both data and label for better representation learning, which also enables the model more robust to the extent of label sparsity. Simple yet effective, the proposed PointMatch achieves the state-of-the-art performance under various weakly-supervised schemes on both ScanNet-v2 and S3DIS datasets, especially on the settings with extremely sparse labels, e.g. surpassing SQN by 21.2% and 17.2% on the 0.01% and 0.1% setting of ScanNet-v2, respectively.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 49 of its 62 references that are in the map. First posted on arXiv 22 Feb 2022.

Builds on

49 of 62 references.

References · 49

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  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. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  8. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  9. 2020Point Transformercited by 1,462
  10. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  11. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  12. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
37 more
  1. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  2. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  3. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  4. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  5. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  6. 2020PCT: Point cloud transformercited by 730
  7. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  8. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  9. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  10. 2020PointGroup: Dual-Set Point Grouping for 3D Instance Segmentationcited by 318
  11. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  12. 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
  13. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  14. 2020Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Datacited by 179
  15. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 178
  16. 2020OccuSeg: Occupancy-aware 3D Instance Segmentationcited by 177
  17. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  18. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  19. 2017Learning Discrete Representations via Information Maximizing Self-Augmented Trainingcited by 149
  20. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  21. 20203DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detectioncited by 89
  22. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  23. 2021PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Trainingcited by 80
  24. 2020Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Cloudscited by 71
  25. 2019Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentationcited by 68
  26. 2021Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptationcited by 67
  27. 2020Self-Supervised Few-Shot Learning on Point Cloudscited by 66
  28. 2021SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Cloudscited by 64
  29. 2019Spherical Kernel for Efficient Graph Convolution on 3D Point Cloudscited by 57
  30. 2020FPConv: Learning Local Flattening for Point Convolutioncited by 55
  31. 2020DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshescited by 42
  32. 2020P4Contrast: Contrastive Learning with Pairs of Point-Pixel Pairs for RGB-D Scene Understandingcited by 41
  33. 2018VoxSegNet: Volumetric CNNs for Semantic Part Segmentation of 3D Shapescited by 37
  34. 2020SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentationcited by 30
  35. 2020Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenescited by 26
  36. 2021Superpoint-guided Semi-supervised Semantic Segmentation of 3D Point Cloudscited by 19
  37. 2021Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approachcited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 1; 2025: 1; 2026: 1.

7 papers.

  1. 2023Advancements in Point Cloud Data Augmentation for Deep Learning: A Surveycited by 24
  2. 2023PointDC:Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-modal Distillation and Super-Voxel Clusteringcited by 15
  3. 2023Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentationcited by 5
  4. 2024Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentationcited by 2
  5. 2023You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understandingcited by 0
  6. 2025Integrating SAM Supervision for 3D Weakly Supervised Point Cloud Segmentationcited by 0
  7. 2026Data-Efficient Semantic Segmentation of 3D Point Clouds via Open-Vocabulary Image Segmentation-based Pseudo-Labelingcited by 0