mlsanityData to 7 Oct 2026

Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labels

arXiv 2004.04091 ↗First posted 8 Apr 2020cs.CVcited by 45

Not on the map. Why?

Abstract (arXiv)

Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks. The success of existing approaches is attributed to deep network design and large amount of labelled training data, where the latter is assumed to be always available. However, obtaining 3d point cloud segmentation labels is often very costly in practice. In this work, we propose a weakly supervised point cloud segmentation approach which requires only a tiny fraction of points to be labelled in the training stage. This is made possible by learning gradient approximation and exploitation of additional spatial and color smoothness constraints. Experiments are done on three public datasets with different degrees of weak supervision. In particular, our proposed method can produce results that are close to and sometimes even better than its fully supervised counterpart with 10× fewer labels.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 15; 2022: 15; 2023: 13; 2024: 0; 2025: 2.

45 papers.

Sort:

  1. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  2. 2021SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Cloudscited by 64
  3. 2021SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Networkcited by 54
  4. 2021ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentationcited by 52
  5. 2022SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Cloudscited by 49
  6. 2021Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysiscited by 47
  7. 2021Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Modelscited by 41
  8. 2022LESS: Label-Efficient Semantic Segmentation for LiDAR Point Cloudscited by 41
  9. 2023GrowSP: Unsupervised Semantic Segmentation of 3D Point Cloudscited by 34
  10. 20213D Spatial Recognition without Spatially Labeled 3Dcited by 31
  11. 2021Multimodal Semi-Supervised Learning for 3D Objectscited by 24
  12. 2022Interactive Object Segmentation in 3D Point Cloudscited by 23
33 more
  1. 2021Superpoint-guided Semi-supervised Semantic Segmentation of 3D Point Cloudscited by 19
  2. 2021Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approachcited by 17
  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. 2023BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentationcited by 14
  6. 2022Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learningcited by 13
  7. 2022Learning Inter-Superpoint Affinity for Weakly Supervised 3D Instance Segmentationcited by 13
  8. 2023All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentationcited by 13
  9. 2021A new weakly supervised approach for ALS point cloud semantic segmentationcited by 12
  10. 2023CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentationcited by 12
  11. 2023Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentationcited by 11
  12. 2022GaIA: Graphical Information Gain based Attention Network for Weakly Supervised Point Cloud Semantic Segmentationcited by 9
  13. 2022Semi-supervised 3D shape segmentation with multilevel consistency and part substitutioncited by 8
  14. 2023ClickSeg: 3D Instance Segmentation with Click-Level Weak Annotationscited by 7
  15. 2023Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentationcited by 7
  16. 2025Unsupervised deep learning for semantic segmentation of multispectral LiDAR forest point cloudscited by 7
  17. 2022SoftPool++: An Encoder-Decoder Network for Point Cloud Completioncited by 6
  18. 2021Point Discriminative Learning for Data-efficient 3D Point Cloud Analysiscited by 5
  19. 2022Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentationcited by 5
  20. 2022One Class One Click: Quasi Scene-level Weakly Supervised Point Cloud Semantic Segmentation with Active Learningcited by 5
  21. 2023Transformation-Invariant Network for Few-Shot Object Detection in Remote Sensing Imagescited by 5
  22. 2021Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Cloudscited by 4
  23. 2025LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectivescited by 4
  24. 2021Weakly Supervised Pseudo-Label assisted Learning for ALS Point Cloud Semantic Segmentationcited by 3
  25. 2022SnapshotNet: Self-supervised Feature Learning for Point Cloud Data Segmentation Using Minimal Labeled Datacited by 3
  26. 2022Open-Set Semi-Supervised Learning for 3D Point Cloud Understandingcited by 3
  27. 2021Cross-Level Cross-Scale Cross-Attention Network for Point Cloud Representationcited by 1
  28. 2023From CAD models to soft point cloud labels: An automatic annotation pipeline for cheaply supervised 3D semantic segmentationcited by 1
  29. 2022CompleteDT: Point Cloud Completion with Dense Augment Inference Transformerscited by 0
  30. 2022Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxescited by 0
  31. 2023You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understandingcited by 0
  32. 2023A Review and A Robust Framework of Data-Efficient 3D Scene Parsing with Traditional/Learned 3D Descriptorscited by 0
  33. 2023Weakly Supervised Point Cloud Segmentation via Conservative Propagation of Scene-level Labelscited by 0