mlsanityData to 14 Oct 2026

GeoMask3D: Geometrically Informed Mask Selection for Self-Supervised Point Cloud Learning in 3D

arXiv 2405.12419 ↗First posted 20 May 2024cs.CV cs.LGcited by 3

On the map: Knowledge distillation → Detection and dense prediction distillation

Abstract (arXiv)

We introduce a pioneering approach to self-supervised learning for point clouds, employing a geometrically informed mask selection strategy called GeoMask3D (GM3D) to boost the efficiency of Masked Auto Encoders (MAE). Unlike the conventional method of random masking, our technique utilizes a teacher-student model to focus on intricate areas within the data, guiding the model's focus toward regions with higher geometric complexity. This strategy is grounded in the hypothesis that concentrating on harder patches yields a more robust feature representation, as evidenced by the improved performance on downstream tasks. Our method also presents a complete-to-partial feature-level knowledge distillation technique designed to guide the prediction of geometric complexity utilizing a comprehensive context from feature-level information. Extensive experiments confirm our method's superiority over State-Of-The-Art (SOTA) baselines, demonstrating marked improvements in classification, and few-shot tasks.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation. Builds on 32 of its 37 references that are in the map. First posted on arXiv 20 May 2024.

Builds on

32 of 37 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?16 Dec

Other references · 31

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  8. 2020Point Transformercited by 1,470
  9. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  10. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  11. 2020PCT: Point cloud transformercited by 732
  12. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
19 more
  1. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  2. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  3. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  4. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 264
  5. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  6. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  7. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  8. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  9. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 144
  10. 2023PointGPT: Auto-regressively Generative Pre-training from Point Cloudscited by 115
  11. 2019Multi-view PointNet for 3D Scene Understandingcited by 76
  12. 2020Self-Supervised Few-Shot Learning on Point Cloudscited by 66
  13. 2021PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysiscited by 58
  14. 2023Hard Patches Mining for Masked Image Modelingcited by 57
  15. 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
  16. 2023Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoderscited by 42
  17. 2022Masked Autoencoders in 3D Point Cloud Representation Learningcited by 30
  18. 2023Self-supervised Learning for Pre-Training 3D Point Clouds: A Surveycited by 21
  19. 20233DCoMPaT++: An improved Large-scale 3D Vision Dataset for Compositional Recognitioncited by 21

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025Spectral Informed Mamba for Robust Point Cloud Processingcited by 10
  2. 2025SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Cloudscited by 4
  3. 2025Purge-Gate: Backpropagation-Free Test-Time Adaptation for Point Clouds Classification via Token Purgingcited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2023Self-supervised adversarial masking for 3D point cloud representation learning
  2. 2025PointGAC: Geometric-Aware Codebook for Masked Point Cloud Modeling
  3. 2025Sonata: Self-Supervised Learning of Reliable Point Representations
  4. 2025Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning
  5. 2026Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds
  6. 2025Foundry: Distilling 3D Foundation Models for the Edge
  7. 2024PMT-MAE: Dual-Branch Self-Supervised Learning with Distillation for Efficient Point Cloud Classification
  8. 2026Less Context, Better Geometry: Masked Geometric Encoder for Robust 3D Foundation Models