mlsanityData to 14 Oct 2026

Masked Surfel Prediction for Self-Supervised Point Cloud Learning

arXiv 2207.03111 ↗First posted 7 Jul 2022cs.CV cs.AIcited by 15

Not on the map. Why?

Abstract (arXiv)

Masked auto-encoding is a popular and effective self-supervised learning approach to point cloud learning. However, most of the existing methods reconstruct only the masked points and overlook the local geometry information, which is also important to understand the point cloud data. In this work, we make the first attempt, to the best of our knowledge, to consider the local geometry information explicitly into the masked auto-encoding, and propose a novel Masked Surfel Prediction (MaskSurf) method. Specifically, given the input point cloud masked at a high ratio, we learn a transformer-based encoder-decoder network to estimate the underlying masked surfels by simultaneously predicting the surfel positions (i.e., points) and per-surfel orientations (i.e., normals). The predictions of points and normals are supervised by the Chamfer Distance and a newly introduced Position-Indexed Normal Distance in a set-to-set manner. Our MaskSurf is validated on six downstream tasks under three fine-tuning strategies. In particular, MaskSurf outperforms its closest competitor, Point-MAE, by 1.2% on the real-world dataset of ScanObjectNN under the OBJ-BG setting, justifying the advantages of masked surfel prediction over masked point cloud reconstruction. Codes will be available at https://github.com/YBZh/MaskSurf.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 59 of its 76 references that are in the map. First posted on arXiv 7 Jul 2022.

Builds on

59 of 76 references.

References · 59

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  8. 2017Mask R-CNNcited by 7,277
  9. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  10. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  11. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  12. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
38 more
  1. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  3. 2015Fast R-CNNcited by 2,933
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  8. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  9. 2020Point Transformercited by 1,470
  10. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  11. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  12. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,322
  13. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  14. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  15. 2020In Search of Lost Domain Generalizationcited by 1,054
  16. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  17. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  18. 2020PCT: Point cloud transformercited by 732
  19. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  20. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 576
  21. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  22. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  23. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  24. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  25. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 264
  26. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  27. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  28. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  29. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  30. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  31. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  32. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  33. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  34. 20183D Point Capsule Networkscited by 106
  35. 2018Multiresolution Tree Networks for 3D Point Cloud Processingcited by 91
  36. 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
  37. 2022Surface Representation for Point Cloudscited by 84
  38. 2020Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Cloudscited by 75

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 8; 2024: 1; 2025: 4.

15 papers.

Sort:

  1. 2023MedShapeNet -- A Large-Scale Dataset of 3D Medical Shapes for Computer Visioncited by 32
  2. 2023Self-supervised Learning for Pre-Training 3D Point Clouds: A Surveycited by 21
  3. 20233D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretrainingcited by 13
  4. 2022MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistencycited by 12
  5. 2022Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learningcited by 9
  6. 2023Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learningcited by 6
  7. 2023PointGame: Geometrically and Adaptively Masked Auto-Encoder on Point Cloudscited by 4
  8. 2024MaskLRF: Self-supervised Pretraining via Masked Autoencoding of Local Reference Frames for Rotation-invariant 3D Point Set Analysiscited by 4
  9. 2023Multi-View Representation is What You Need for Point-Cloud Pre-Trainingcited by 3
  10. 2025Token Adaptation via Side Graph Convolution for Efficient Fine-tuning of 3D Point Cloud Transformerscited by 2
  11. 2025Masked Clustering Prediction for Unsupervised Point Cloud Pre-trainingcited by 2
  12. 2025HFBRI-MAE: Handcrafted Feature Based Rotation-Invariant Masked Autoencoder for 3D Point Cloud Analysiscited by 1
3 more
  1. 2025Physics-Driven Local-Whole Elastic Deformation Modeling for Point Cloud Representation Learningcited by 1
  2. 2023Self-Supervised Learning for Point Clouds Data: A Surveycited by 0
  3. 2023Geometry Aware Field-to-field Transformations for 3D Semantic Segmentationcited by 0