mlsanityData to 7 Oct 2026

Semi-supervised 3D shape segmentation with multilevel consistency and part substitution

arXiv 2204.08824 ↗First posted 19 Apr 2022cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

The lack of fine-grained 3D shape segmentation data is the main obstacle to developing learning-based 3D segmentation techniques. We propose an effective semi-supervised method for learning 3D segmentations from a few labeled 3D shapes and a large amount of unlabeled 3D data. For the unlabeled data, we present a novel multilevel consistency loss to enforce consistency of network predictions between perturbed copies of a 3D shape at multiple levels: point-level, part-level, and hierarchical level. For the labeled data, we develop a simple yet effective part substitution scheme to augment the labeled 3D shapes with more structural variations to enhance training. Our method has been extensively validated on the task of 3D object semantic segmentation on PartNet and ShapeNetPart, and indoor scene semantic segmentation on ScanNet. It exhibits superior performance to existing semi-supervised and unsupervised pre-training 3D approaches. Our code and trained models are publicly available at https://github.com/isunchy/semi_supervised_3d_segmentation.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 52 of its 82 references that are in the map. First posted on arXiv 19 Apr 2022.

Builds on

52 of 82 references.

References · 52

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  7. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  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. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  11. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  12. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
38 more
  1. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  2. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  3. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  4. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  5. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
  6. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 375
  7. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  8. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  9. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  10. 2019CvxNet: Learnable Convex Decompositioncited by 173
  11. 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 123
  12. 2020Guided Collaborative Training for Pixel-wise Semi-Supervised Learningcited by 120
  13. 20183DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentationcited by 118
  14. 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 118
  15. 20183D Point Capsule Networkscited by 106
  16. 2020PointMixup: Augmentation for Point Cloudscited by 104
  17. 2019BAE-NET: Branched Autoencoder for Shape Co-Segmentationcited by 89
  18. 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
  19. 2018MeshCNN: A Network with an Edgecited by 69
  20. 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
  21. 2020PointAugment: an Auto-Augmentation Framework for Point Cloud Classificationcited by 65
  22. 20163D Shape Segmentation with Projective Convolutional Networkscited by 63
  23. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  24. 2017O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysiscited by 47
  25. 2020Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labelscited by 45
  26. 2020Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentationcited by 40
  27. 2020Deep Octree-based CNNs with Output-Guided Skip Connections for 3D Shape and Scene Completioncited by 33
  28. 2018Multi-directional Geodesic Neural Networks via Equivariant Convolutioncited by 32
  29. 2020Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discriminationcited by 31
  30. 2020Label-Efficient Learning on Point Clouds using Approximate Convex Decompositionscited by 27
  31. 2018SCORES: Shape Composition with Recursive Substructure Priorscited by 23
  32. 2019StructEdit: Learning Structural Shape Variationscited by 23
  33. 2020Joint Supervised and Self-Supervised Learning for 3D Real-World Challengescited by 21
  34. 2019Local Deep Implicit Functions for 3D Shapecited by 18
  35. 2017Learning Hierarchical Shape Segmentation and Labeling from Online Repositoriescited by 11
  36. 2018Learning to Group and Label Fine-Grained Shape Componentscited by 9
  37. 2015Data-Driven Shape Analysis and Processingcited by 8
  38. 2020FAME: 3D Shape Generation via Functionality-Aware Model Evolutioncited by 8

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 0; 2024: 4; 2025: 1.

8 papers.

  1. 2022PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Modelscited by 117
  2. 2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 92
  3. 2024Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Drivingcited by 53
  4. 2024View-Consistent Hierarchical 3D Segmentation Using Ultrametric Feature Fieldscited by 8
  5. 2024Self-supervised Learning of Hybrid Part-aware 3D Representations of 2D Gaussians and Superquadricscited by 8
  6. 2024ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentationcited by 5
  7. 2022SHRED: 3D Shape Region Decomposition with Learned Local Operationscited by 1
  8. 2025SAR2Struct: Extracting 3D Semantic Structural Representation of Aircraft Targets from Single-View SAR Imagecited by 0