mlsanityData to 7 Oct 2026

Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning

arXiv 2211.06841 ↗First posted 13 Nov 2022cs.CV cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Masked autoencoder has demonstrated its effectiveness in self-supervised point cloud learning. Considering that masking is a kind of corruption, in this work we explore a more general denoising autoencoder for point cloud learning (Point-DAE) by investigating more types of corruptions beyond masking. Specifically, we degrade the point cloud with certain corruptions as input, and learn an encoder-decoder model to reconstruct the original point cloud from its corrupted version. Three corruption families (ie, density/masking, noise, and affine transformation) and a total of fourteen corruption types are investigated with traditional non-Transformer encoders. Besides the popular masking corruption, we identify another effective corruption family, ie, affine transformation. The affine transformation disturbs all points globally, which is complementary to the masking corruption where some local regions are dropped. We also validate the effectiveness of affine transformation corruption with the Transformer backbones, where we decompose the reconstruction of the complete point cloud into the reconstructions of detailed local patches and rough global shape, alleviating the position leakage problem in the reconstruction. Extensive experiments on tasks of object classification, few-shot learning, robustness testing, part segmentation, and 3D object detection validate the effectiveness of the proposed method. The codes are available at urlhttps://github.com/YBZh/Point-DAE.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 76 of its 109 references that are in the map. First posted on arXiv 13 Nov 2022.

Builds on

76 of 109 references.

References · 76

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  6. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  7. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  8. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  9. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  10. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  11. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  12. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
38 more
  1. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  2. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  4. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  5. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  6. 2020Point Transformercited by 1,462
  7. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  8. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,305
  9. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  10. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  11. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  12. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  13. 2017A Survey on Multi-Task Learningcited by 838
  14. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  15. 2020PCT: Point cloud transformercited by 730
  16. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  17. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  18. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  19. 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
  20. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  21. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  22. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  23. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  24. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  25. 2022Masked Autoencoders As Spatiotemporal Learnerscited by 428
  26. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  27. 2018PCN: Point Completion Networkcited by 382
  28. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  29. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  30. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
  31. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  32. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  33. 2018PU-Net: Point Cloud Upsampling Networkcited by 208
  34. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  35. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  36. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  37. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  38. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155

50 most cited of 76 All 76 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 1; 2025: 3; 2026: 2.

9 papers.

  1. 2023Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Modelscited by 67
  2. 2023Self-supervised Learning for Pre-Training 3D Point Clouds: A Surveycited by 21
  3. 2025Masked Clustering Prediction for Unsupervised Point Cloud Pre-trainingcited by 2
  4. 2024To Supervise or Not to Supervise: Understanding and Addressing the Key Challenges of Point Cloud Transfer Learningcited by 1
  5. 2025Physics-Driven Local-Whole Elastic Deformation Modeling for Point Cloud Representation Learningcited by 1
  6. 2025GFT: Graph Feature Tuning for Efficient Point Cloud Analysiscited by 1
  7. 2026From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric Datacited by 1
  8. 2023Self-Supervised Learning for Point Clouds Data: A Surveycited by 0
  9. 2026Point-Selection Fine-Tuning Framework for Robust Point Cloud Classificationcited by 0