mlsanityData to 7 Oct 2026

Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey

arXiv 2202.13589 ↗First posted 28 Feb 2022cs.CV cs.AIcited by 54

Not on the map. Why?

Abstract (arXiv)

Point cloud data have been widely explored due to its superior accuracy and robustness under various adverse situations. Meanwhile, deep neural networks (DNNs) have achieved very impressive success in various applications such as surveillance and autonomous driving. The convergence of point cloud and DNNs has led to many deep point cloud models, largely trained under the supervision of large-scale and densely-labelled point cloud data. Unsupervised point cloud representation learning, which aims to learn general and useful point cloud representations from unlabelled point cloud data, has recently attracted increasing attention due to the constraint in large-scale point cloud labelling. This paper provides a comprehensive review of unsupervised point cloud representation learning using DNNs. It first describes the motivation, general pipelines as well as terminologies of the recent studies. Relevant background including widely adopted point cloud datasets and DNN architectures is then briefly presented. This is followed by an extensive discussion of existing unsupervised point cloud representation learning methods according to their technical approaches. We also quantitatively benchmark and discuss the reviewed methods over multiple widely adopted point cloud datasets. Finally, we share our humble opinion about several challenges and problems that could be pursued in future research in unsupervised point cloud representation learning. A project associated with this survey has been built at https://github.com/xiaoaoran/3d_url_survey.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). Builds on 102 of its 162 references that are in the map. First posted on arXiv 28 Feb 2022.

Builds on

102 of 162 references.

References · 102

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  8. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  9. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  10. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  11. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  12. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
38 more
  1. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  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. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  6. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  8. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  9. 2020Point Transformercited by 1,462
  10. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  11. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  12. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  13. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  14. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  15. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  16. 2020Self-supervised Learning: Generative or Contrastivecited by 693
  17. 2017Dynamic Routing Between Capsulescited by 689
  18. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 656
  19. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  20. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  21. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  22. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  23. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  24. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  25. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  26. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  27. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  28. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  29. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  30. 2019ScanRefer: 3D Object Localization in RGB-D Scans using Natural Languagecited by 446
  31. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  32. 2018PCN: Point Completion Networkcited by 382
  33. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  34. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  35. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 333
  36. 2021One Million Scenes for Autonomous Driving: ONCE Datasetcited by 218
  37. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  38. 2021A Large-Scale Study on Unsupervised Spatiotemporal Representation Learningcited by 214

50 most cited of 102 All 102 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 12; 2024: 17; 2025: 19; 2026: 5.

54 papers.

Sort:

By area:

  1. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 123
  2. 2024Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learningcited by 43
  3. 2023Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioningcited by 38
  4. 20244D Contrastive Superflows are Dense 3D Representation Learnerscited by 32
  5. 2024End-to-End Autonomous Driving without Costly Modularization and 3D Manual Annotationcited by 27
  6. 2023Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learningcited by 23
  7. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  8. 2025LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenescited by 19
  9. 2023Point2SSM: Learning Morphological Variations of Anatomies from Point Cloudcited by 14
  10. 2023Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representationcited by 12
  11. 2024An Empirical Study of Training State-of-the-Art LiDAR Segmentation Modelscited by 12
  12. 2023T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learningcited by 11
38 more
  1. 2024Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understandingcited by 11
  2. 2025LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Drivingcited by 11
  3. 2022Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learningcited by 9
  4. 20253EED: Ground Everything Everywhere in 3Dcited by 8
  5. 2025Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representationscited by 7
  6. 2024FAPNet: An Effective Frequency Adaptive Point-based Eye Trackercited by 6
  7. 2024Deep Learning on 3D Semantic Segmentation: A Detailed Reviewcited by 6
  8. 2025MoST: Efficient Monarch Sparse Tuning for 3D Representation Learningcited by 6
  9. 2023Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Surveycited by 5
  10. 2023Novel class discovery meets foundation models for 3D semantic segmentationcited by 4
  11. 2024MaskLRF: Self-supervised Pretraining via Masked Autoencoding of Local Reference Frames for Rotation-invariant 3D Point Set Analysiscited by 4
  12. 2024Explainability of Point Cloud Neural Networks Using SMILE: Statistical Model-Agnostic Interpretability with Local Explanationscited by 4
  13. 2024Unsupervised semantic segmentation of urban high-density multispectral point cloudscited by 4
  14. 2025LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectivescited by 4
  15. 2025Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systemscited by 4
  16. 2023Multi-View Representation is What You Need for Point-Cloud Pre-Trainingcited by 3
  17. 2024GeoMask3D: Geometrically Informed Mask Selection for Self-Supervised Point Cloud Learning in 3Dcited by 3
  18. 2023Self-supervised Learning of Rotation-invariant 3D Point Set Features using Transformer and its Self-distillationcited by 2
  19. 2024Training-Free Point Cloud Recognition Based on Geometric and Semantic Information Fusioncited by 2
  20. 2025Aligning Instance-Semantic Sparse Representation towards Unsupervised Object Segmentation and Shape Abstraction with Repeatable Primitivescited by 2
  21. 2025Domain-aware Category-level Geometry Learning Segmentation for 3D Point Cloudscited by 2
  22. 2025Weakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Drivingcited by 2
  23. 2023PointJEM: Self-supervised Point Cloud Understanding for Reducing Feature Redundancy via Joint Entropy Maximizationcited by 1
  24. 2024To Supervise or Not to Supervise: Understanding and Addressing the Key Challenges of Point Cloud Transfer Learningcited by 1
  25. 2024SR-CurvANN: Advancing 3D Surface Reconstruction through Curvature-Aware Neural Networkscited by 1
  26. 2024Towards Modality-agnostic Label-efficient Segmentation with Entropy-Regularized Distribution Alignmentcited by 1
  27. 2025Incorporating Inductive Biases to Energy-based Generative Modelscited by 1
  28. 2025Parameter-Efficient CLIP Adaptation for 3D Understanding via Unified Tokenizationcited by 1
  29. 2025HyPCV-Former: Hyperbolic Spatio-Temporal Transformer for 3D Point Cloud Video Anomaly Detectioncited by 1
  30. 2025HeartFormer: Semantic-Aware Dual-Structure Transformers for 3D Four-Chamber Cardiac Point Cloud Reconstructioncited by 1
  31. 2026PointGS: Semantic-Consistent Unsupervised 3D Point Cloud Segmentation with 3D Gaussian Splattingcited by 1
  32. 2024Region-Transformer: Self-Attention Region Based Class-Agnostic Point Cloud Segmentationcited by 0
  33. 2024Geometry Distributionscited by 0
  34. 2025Attention-Guided Multi-Scale Local Reconstruction for Point Clouds via Masked Autoencoder Self-Supervised Learningcited by 0
  35. 2025A Multi-View High-Resolution Foot-Ankle Complex Point Cloud Dataset During Gait for Occlusion-Robust 3D Completioncited by 0
  36. 2025White Aggregation and Restoration for Few-shot 3D Point Cloud Semantic Segmentationcited by 0
  37. 2025GauSSmart: Enhanced 3D Reconstruction through 2D Foundation Models and Geometric Filteringcited by 0
  38. 2025Symmetria: A Synthetic Dataset for Learning in Point Cloudscited by 0

50 most cited of 54 All 54 (JSON)