mlsanityData to 14 Oct 2026

Attention Models for Point Clouds in Deep Learning: A Survey

arXiv 2102.10788 ↗First posted 22 Feb 2021cs.CV cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Recently, the advancement of 3D point clouds in deep learning has attracted intensive research in different application domains such as computer vision and robotic tasks. However, creating feature representation of robust, discriminative from unordered and irregular point clouds is challenging. In this paper, our ultimate goal is to provide a comprehensive overview of the point clouds feature representation which uses attention models. More than 75+ key contributions in the recent three years are summarized in this survey, including the 3D objective detection, 3D semantic segmentation, 3D pose estimation, point clouds completion etc. We provide a detailed characterization (1) the role of attention mechanisms, (2) the usability of attention models into different tasks, (3) the development trend of key technology.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 40 of its 83 references that are in the map. First posted on arXiv 22 Feb 2021.

Builds on

40 of 83 references.

References · 40

  1. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  2. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,026
  3. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
  4. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  5. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  6. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 321
  7. 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 164
  8. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  9. 2020FLOT: Scene Flow on Point Clouds Guided by Optimal Transportcited by 129
  10. 2019An Attentive Survey of Attention Modelscited by 124
  11. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  12. 2019TANet: Robust 3D Object Detection from Point Clouds with Triple Attentioncited by 108
28 more
  1. 2020Point Cloud Completion by Skip-attention Network with Hierarchical Foldingcited by 106
  2. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  3. 20183DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registrationcited by 103
  4. 2019Attention in Natural Language Processingcited by 101
  5. 2020MLCVNet: Multi-Level Context VoteNet for 3D Object Detectioncited by 80
  6. 2016Towards an integration of deep learning and neurosciencecited by 78
  7. 2019DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registrationcited by 77
  8. 2020Detail Preserved Point Cloud Completion via Separated Feature Aggregationcited by 70
  9. 2019PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrievalcited by 68
  10. 2020SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognitioncited by 66
  11. 2020DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalizationcited by 42
  12. 2019PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Cloudscited by 38
  13. 2018PVNet: A Joint Convolutional Network of Point Cloud and Multi-View for 3D Shape Recognitioncited by 36
  14. 2020Hierarchical Attention Learning of Scene Flow in 3D Point Cloudscited by 35
  15. 2020PWCLO-Net: Deep LiDAR Odometry in 3D Point Clouds Using Hierarchical Embedding Mask Optimizationcited by 35
  16. 2019L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attentioncited by 32
  17. 2020SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimizationcited by 26
  18. 2020PIC-Net: Point Cloud and Image Collaboration Network for Large-Scale Place Recognitioncited by 16
  19. 2016Survey on the attention based RNN model and its applications in computer visioncited by 15
  20. 2020RSKDD-Net: Random Sample-based Keypoint Detector and Descriptorcited by 12
  21. 2020Neighbourhood-Insensitive Point Cloud Normal Estimation Networkcited by 8
  22. 2020End-to-End 3D Point Cloud Learning for Registration Task Using Virtual Correspondencescited by 8
  23. 20196D Pose Estimation with Correlation Fusioncited by 6
  24. 20193D Graph Embedding Learning with a Structure-aware Loss Function for Point Cloud Semantic Instance Segmentationcited by 4
  25. 2020MANet: Multimodal Attention Network based Point- View fusion for 3D Shape Recognitioncited by 2
  26. 2020Geometric Attention for Prediction of Differential Properties in 3D Point Cloudscited by 2
  27. 2020PAM:Point-wise Attention Module for 6D Object Pose Estimationcited by 2
  28. 2020SHREC 2020 track: 6D Object Pose Estimationcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 1.

6 papers.

  1. 2022LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsamplingcited by 8
  2. 20233D Multiple Object Tracking on Autonomous Driving: A Literature Reviewcited by 4
  3. 2023Graph Structure from Point Clouds: Geometric Attention is All You Needcited by 2
  4. 2024Curvature Informed Furthest Point Samplingcited by 1
  5. 2022Using Gradient to Boost the Generalization Performance of Deep Learning Models for Fluid Dynamicscited by 0
  6. 2023AGAR: Attention Graph-RNN for Adaptative Motion Prediction of Point Clouds of Deformable Objectscited by 0