mlsanityData to 7 Oct 2026

Contrastive Boundary Learning for Point Cloud Segmentation

arXiv 2203.05272 ↗First posted 10 Mar 2022cs.CVcited by 56

Not on the map. Why?

Abstract (arXiv)

Point cloud segmentation is fundamental in understanding 3D environments. However, current 3D point cloud segmentation methods usually perform poorly on scene boundaries, which degenerates the overall segmentation performance. In this paper, we focus on the segmentation of scene boundaries. Accordingly, we first explore metrics to evaluate the segmentation performance on scene boundaries. To address the unsatisfactory performance on boundaries, we then propose a novel contrastive boundary learning (CBL) framework for point cloud segmentation. Specifically, the proposed CBL enhances feature discrimination between points across boundaries by contrasting their representations with the assistance of scene contexts at multiple scales. By applying CBL on three different baseline methods, we experimentally show that CBL consistently improves different baselines and assists them to achieve compelling performance on boundaries, as well as the overall performance, eg in mIoU. The experimental results demonstrate the effectiveness of our method and the importance of boundaries for 3D point cloud segmentation. Code and model will be made publicly available at https://github.com/LiyaoTang/contrastBoundary.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Builds on 82 of its 111 references that are in the map. First posted on arXiv 10 Mar 2022.

Builds on

82 of 111 references.

References · 82

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  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. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  7. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  10. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  11. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  12. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
38 more
  1. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  2. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  3. 2020PCT: Point cloud transformercited by 730
  4. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  5. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  6. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  7. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  8. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  9. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  10. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
  11. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  12. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  13. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  14. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  15. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  16. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 231
  17. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  18. 2017Submanifold Sparse Convolutional Networkscited by 223
  19. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  20. 2021Boundary IoU: Improving Object-Centric Image Segmentation Evaluationcited by 186
  21. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 178
  22. 2020OccuSeg: Occupancy-aware 3D Instance Segmentationcited by 177
  23. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  24. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  25. 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
  26. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  27. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  28. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  29. 20183DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentationcited by 118
  30. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  31. 2017ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scanscited by 103
  32. 2020Virtual Multi-view Fusion for 3D Semantic Segmentationcited by 99
  33. 2019Analyzing and Improving Representations with the Soft Nearest Neighbor Losscited by 95
  34. 2020Contrastive Learning for Label-Efficient Semantic Segmentationcited by 93
  35. 2019BAE-NET: Branched Autoencoder for Shape Co-Segmentationcited by 89
  36. 2020A Closer Look at Local Aggregation Operators in Point Cloud Analysiscited by 87
  37. 2018Recurrent Slice Networks for 3D Segmentation of Point Cloudscited by 82
  38. 2017Deep Projective 3D Semantic Segmentationcited by 81

50 most cited of 82 All 82 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 10; 2023: 18; 2024: 10; 2025: 11; 2026: 7.

56 papers.

Sort:

By area:

  1. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  2. 2023OmniVec: Learning robust representations with cross modal sharingcited by 44
  3. 2022Meta Architecture for Point Cloud Analysiscited by 39
  4. 2022GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentationcited by 36
  5. 2024Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Cloudscited by 24
  6. 2023Clustering based Point Cloud Representation Learning for 3D Analysiscited by 23
  7. 2022PointVector: A Vector Representation In Point Cloud Analysiscited by 21
  8. 2023Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 21
  9. 20233DTeethSeg'22: 3D Teeth Scan Segmentation and Labeling Challengecited by 14
  10. 2023All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentationcited by 13
  11. 2025OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learningcited by 13
  12. 2022GaIA: Graphical Information Gain based Attention Network for Weakly Supervised Point Cloud Semantic Segmentationcited by 9
38 more
  1. 2022GeoSegNet: Point Cloud Semantic Segmentation via Geometric Encoder-Decoder Modelingcited by 8
  2. 2023ViPFormer: Efficient Vision-and-Pointcloud Transformer for Unsupervised Pointcloud Understandingcited by 8
  3. 20253D Dental Model Segmentation with Geometrical Boundary Preservingcited by 7
  4. 2023Region-Enhanced Feature Learning for Scene Semantic Segmentationcited by 6
  5. 2023Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentationcited by 6
  6. 2025Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Fieldcited by 6
  7. 2023Full Point Encoding for Local Feature Aggregation in 3D Point Cloudscited by 5
  8. 2025BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysiscited by 5
  9. 2023PRISE: Demystifying Deep Lucas-Kanade with Strongly Star-Convex Constraints for Multimodel Image Alignmentcited by 4
  10. 2023Collect-and-Distribute Transformer for 3D Point Cloud Analysiscited by 4
  11. 2024Subspace Prototype Guidance for Mitigating Class Imbalance in Point Cloud Semantic Segmentationcited by 4
  12. 2025Adaptive Margin Contrastive Learning for Ambiguity-aware 3D Semantic Segmentationcited by 4
  13. 2025On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentationcited by 4
  14. 2022Push-the-Boundary: Boundary-aware Feature Propagation for Semantic Segmentation of 3D Point Cloudscited by 3
  15. 2023SAT: Size-Aware Transformer for 3D Point Cloud Semantic Segmentationcited by 3
  16. 2023Small but Mighty: Enhancing 3D Point Clouds Semantic Segmentation with U-Next Frameworkcited by 3
  17. 2023Multi-View Representation is What You Need for Point-Cloud Pre-Trainingcited by 3
  18. 2023PointHR: Exploring High-Resolution Architectures for 3D Point Cloud Segmentationcited by 3
  19. 2024Debiasing Machine Unlearning with Counterfactual Examplescited by 3
  20. 2024ML-SemReg: Boosting Point Cloud Registration with Multi-level Semantic Consistencycited by 3
  21. 2024Deep Loss Convexification for Learning Iterative Modelscited by 3
  22. 2025Cell Instance Segmentation: The Devil Is in the Boundariescited by 3
  23. 2022Uncertainty Estimation for 3D Dense Prediction via Cross-Point Embeddingscited by 2
  24. 2025Domain-aware Category-level Geometry Learning Segmentation for 3D Point Cloudscited by 2
  25. 2023From CAD models to soft point cloud labels: An automatic annotation pipeline for cheaply supervised 3D semantic segmentationcited by 1
  26. 2023GeoSpark: Sparking up Point Cloud Segmentation with Geometry Cluecited by 1
  27. 2023Cloud-RAIN: Point Cloud Analysis with Reflectional Invariancecited by 1
  28. 2024GSTran: Joint Geometric and Semantic Coherence for Point Cloud Segmentationcited by 1
  29. 2024Towards Modality-agnostic Label-efficient Segmentation with Entropy-Regularized Distribution Alignmentcited by 1
  30. 2024CP-VoteNet: Contrastive Prototypical VoteNet for Few-Shot Point Cloud Object Detectioncited by 1
  31. 2025Ambiguity-aware Point Cloud Segmentation by Adaptive Margin Contrastive Learningcited by 1
  32. 2022Diffusion Unit: Interpretable Edge Enhancement and Suppression Learning for 3D Point Cloud Segmentationcited by 0
  33. 2022Adaptive Edge-to-Edge Interaction Learning for Point Cloud Analysiscited by 0
  34. 2024Soft Masked Transformer for Point Cloud Processing with Skip Attention-Based Upsamplingcited by 0
  35. 2024Geometry-guided Feature Learning and Fusion for Indoor Scene Reconstructioncited by 0
  36. 2025UPP: Unified Point-Level Prompting for Robust Point Cloud Analysiscited by 0
  37. 2025Label-Efficient Point Cloud Segmentation with Active Learningcited by 0
  38. 2026G2P: Gaussian-to-Point Attribute Alignment for Boundary-Aware 3D Segmentationcited by 0

50 most cited of 56 All 56 (JSON)