mlsanityData to 7 Oct 2026

3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining

arXiv 2304.06911 ↗First posted 14 Apr 2023cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Masked autoencoders (MAE) have recently been introduced to 3D self-supervised pretraining for point clouds due to their great success in NLP and computer vision. Unlike MAEs used in the image domain, where the pretext task is to restore features at the masked pixels, such as colors, the existing 3D MAE works reconstruct the missing geometry only, i.e, the location of the masked points. In contrast to previous studies, we advocate that point location recovery is inessential and restoring intrinsic point features is much superior. To this end, we propose to ignore point position reconstruction and recover high-order features at masked points including surface normals and surface variations, through a novel attention-based decoder which is independent of the encoder design. We validate the effectiveness of our pretext task and decoder design using different encoder structures for 3D training and demonstrate the advantages of our pretrained networks on various point cloud analysis tasks.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 44 of its 67 references that are in the map. First posted on arXiv 14 Apr 2023.

Builds on

44 of 67 references.

References · 44

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  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. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  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. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  12. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
32 more
  1. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  2. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  3. 2020Point Transformercited by 1,462
  4. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  5. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 891
  6. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  7. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  8. 2020Self-supervised Learning: Generative or Contrastivecited by 693
  9. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  10. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 573
  11. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited 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 502
  14. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  15. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  16. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  17. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
  18. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  19. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  20. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  21. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  22. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  23. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  24. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 166
  25. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  26. 2021FCAF3D: Fully Convolutional Anchor-Free 3D Object Detectioncited by 97
  27. 2020Multimodal Pretraining Unmasked: A Meta-Analysis and a Unified Framework of Vision-and-Language BERTscited by 71
  28. 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
  29. 2022Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learningcited by 46
  30. 2021HPNet: Deep Primitive Segmentation Using Hybrid Representationscited by 35
  31. 2020Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discriminationcited by 31
  32. 2022Masked Surfel Prediction for Self-Supervised Point Cloud Learningcited by 15

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 6; 2025: 4.

13 papers.

Sort:

By area:

  1. 2024Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understandingcited by 46
  2. 2024ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modelingcited by 34
  3. 2023EEG-based Cognitive Load Classification using Feature Masked Autoencoding and Emotion Transfer Learningcited by 6
  4. 2024Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene Understandingcited by 6
  5. 2024MaskLRF: Self-supervised Pretraining via Masked Autoencoding of Local Reference Frames for Rotation-invariant 3D Point Set Analysiscited by 4
  6. 2025Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene Understandingcited by 4
  7. 2023Multi-View Representation is What You Need for Point-Cloud Pre-Trainingcited by 3
  8. 2025Uni4D: A Unified Self-Supervised Learning Framework for Point Cloud Videoscited by 3
  9. 2024Mitigating Prior Shape Bias in Point Clouds via Differentiable Center Learningcited by 1
  10. 2023Instance-aware 3D Semantic Segmentation powered by Shape Generators and Classifierscited by 0
  11. 2024PointCG: Self-supervised Point Cloud Learning via Joint Completion and Generationcited by 0
  12. 2025Unlocking Hidden Potential in Point Cloud Networks with Attention-Guided Grouping-Feature Coordinationcited by 0
1 more
  1. 2025Self-Supervised Masked Autoencoders with Dense-Unet for Coronary Calcium Removal in limited CT Datacited by 0