mlsanityData to 14 Oct 2026

PointGame: Geometrically and Adaptively Masked Auto-Encoder on Point Clouds

arXiv 2303.13100 ↗First posted 23 Mar 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Self-supervised learning is attracting large attention in point cloud understanding. However, exploring discriminative and transferable features still remains challenging due to their nature of irregularity and sparsity. We propose a geometrically and adaptively masked auto-encoder for self-supervised learning on point clouds, termed textitPointGame. PointGame contains two core components: GATE and EAT. GATE stands for the geometrical and adaptive token embedding module; it not only absorbs the conventional wisdom of geometric descriptors that captures the surface shape effectively, but also exploits adaptive saliency to focus on the salient part of a point cloud. EAT stands for the external attention-based Transformer encoder with linear computational complexity, which increases the efficiency of the whole pipeline. Unlike cutting-edge unsupervised learning models, PointGame leverages geometric descriptors to perceive surface shapes and adaptively mines discriminative features from training data. PointGame showcases clear advantages over its competitors on various downstream tasks under both global and local fine-tuning strategies. The code and pre-trained models will be publicly available.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 44 of its 72 references that are in the map. First posted on arXiv 23 Mar 2023.

Builds on

44 of 72 references.

References · 44

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  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. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  8. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  9. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  10. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  11. 2020Point Transformercited by 1,470
  12. 2015Spatial Transformer Networkscited by 1,429
32 more
  1. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
  2. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  3. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  4. 2020PCT: Point cloud transformercited by 732
  5. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  6. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  7. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  8. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  9. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  10. 2014Recurrent Models of Visual Attentioncited by 349
  11. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  12. 2020Exploring Self-attention for Image Recognitioncited by 313
  13. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 264
  14. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  15. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  16. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  17. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  18. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  19. 2021Beyond Self-attention: External Attention using Two Linear Layers for Visual Taskscited by 109
  20. 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
  21. 2020Self-supervised Learning of Point Clouds via Orientation Estimationcited by 72
  22. 2020Self-Supervised Few-Shot Learning on Point Cloudscited by 66
  23. 2021PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysiscited by 58
  24. 2021Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learningcited by 52
  25. 2022Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learningcited by 46
  26. 2021Global and Local Contrastive Self-Supervised Learning for Semantic Segmentation of HR Remote Sensing Imagescited by 31
  27. 2022Masked Autoencoders in 3D Point Cloud Representation Learningcited by 30
  28. 2022Refine-Net: Normal Refinement Neural Network for Noisy Point Cloudscited by 23
  29. 2022Masked Surfel Prediction for Self-Supervised Point Cloud Learningcited by 15
  30. 2022AGConv: Adaptive Graph Convolution on 3D Point Cloudscited by 13
  31. 2022PointSee: Image Enhances Point Cloudcited by 5
  32. 2023PointSmile: Point Self-supervised Learning via Curriculum Mutual Informationcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 3.

4 papers.

  1. 2024PointCG: Self-supervised Point Cloud Learning via Joint Completion and Generationcited by 0
  2. 2025Attention-Guided Multi-Scale Local Reconstruction for Point Clouds via Masked Autoencoder Self-Supervised Learningcited by 0
  3. 2025PointGAC: Geometric-Aware Codebook for Masked Point Cloud Modelingcited by 0
  4. 2025Point-RTD: Replaced Token Denoising for Pretraining Transformer Models on Point Cloudscited by 0