mlsanityData to 14 Oct 2026

Self-Supervised Learning with Multi-View Rendering for 3D Point Cloud Analysis

arXiv 2210.15904 ↗First posted 28 Oct 2022cs.CV cs.AI cs.GRcited by 8

Not on the map. Why?

Abstract (arXiv)

Recently, great progress has been made in 3D deep learning with the emergence of deep neural networks specifically designed for 3D point clouds. These networks are often trained from scratch or from pre-trained models learned purely from point cloud data. Inspired by the success of deep learning in the image domain, we devise a novel pre-training technique for better model initialization by utilizing the multi-view rendering of the 3D data. Our pre-training is self-supervised by a local pixel/point level correspondence loss computed from perspective projection and a global image/point cloud level loss based on knowledge distillation, thus effectively improving upon popular point cloud networks, including PointNet, DGCNN and SR-UNet. These improved models outperform existing state-of-the-art methods on various datasets and downstream tasks. We also analyze the benefits of synthetic and real data for pre-training, and observe that pre-training on synthetic data is also useful for high-level downstream tasks. Code and pre-trained models are available at https://github.com/VinAIResearch/selfsup_pcd.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 48 of its 63 references that are in the map. First posted on arXiv 28 Oct 2022.

Builds on

48 of 63 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  6. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  7. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  8. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  9. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  10. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  11. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  12. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
36 more
  1. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  2. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  3. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
  4. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
  5. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  6. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  7. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  8. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  9. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  10. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  11. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  12. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  13. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 504
  14. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  15. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 310
  16. 2017Submanifold Sparse Convolutional Networkscited by 223
  17. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  18. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  19. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  20. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  21. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  22. 2015Cross Modal Distillation for Supervision Transfercited by 175
  23. 2017Pointwise Convolutional Neural Networkscited by 127
  24. 2020Self-Supervised Learning for Domain Adaptation on Point-Cloudscited by 99
  25. 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
  26. 2020Self-supervised Learning of Point Clouds via Orientation Estimationcited by 72
  27. 2019Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Predictioncited by 66
  28. 2020Self-Supervised Few-Shot Learning on Point Cloudscited by 66
  29. 2021Pri3D: Can 3D Priors Help 2D Representation Learning?cited by 61
  30. 2021SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representationscited by 55
  31. 20213D-to-2D Distillation for Indoor Scene Parsingcited by 48
  32. 2021Learning from 2D: Contrastive Pixel-to-Point Knowledge Transfer for 3D Pretrainingcited by 33
  33. 2019LCD: Learned Cross-Domain Descriptors for 2D-3D Matchingcited by 29
  34. 2020Joint Supervised and Self-Supervised Learning for 3D Real-World Challengescited by 21
  35. 2020Self-supervised Modal and View Invariant Feature Learningcited by 20
  36. 2020Self-supervised Feature Learning by Cross-modality and Cross-view Correspondencescited by 19

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 5; 2024: 1; 2025: 1.

8 papers.

  1. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 125
  2. 2023Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Featurescited by 55
  3. 2023Self-supervised Learning for Pre-Training 3D Point Clouds: A Surveycited by 21
  4. 2025LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Drivingcited by 12
  5. 2022Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learningcited by 9
  6. 2023Point Clouds Are Specialized Images: A Knowledge Transfer Approach for 3D Understandingcited by 3
  7. 2024Pic@Point: Cross-Modal Learning by Local and Global Point-Picture Correspondencecited by 1
  8. 2023Self-Supervised Learning for Point Clouds Data: A Surveycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Self-supervised adversarial masking for 3D point cloud representation learning
  2. 2025Sonata: Self-Supervised Learning of Reliable Point Representations
  3. 2025Self-Supervised Point Cloud Completion based on Multi-View Augmentations of Single Partial Point Cloud
  4. 2023PointMoment:Mixed-Moment-based Self-Supervised Representation Learning for 3D Point Clouds
  5. 2022SeRP: Self-Supervised Representation Learning Using Perturbed Point Clouds
  6. 2022Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learning
  7. 2022Self-Distillation for Unsupervised 3D Domain Adaptation
  8. 2022Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learning