mlsanityData to 7 Oct 2026

Investigating Attention Mechanism in 3D Point Cloud Object Detection

arXiv 2108.00620 ↗First posted 2 Aug 2021cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Object detection in three-dimensional (3D) space attracts much interest from academia and industry since it is an essential task in AI-driven applications such as robotics, autonomous driving, and augmented reality. As the basic format of 3D data, the point cloud can provide detailed geometric information about the objects in the original 3D space. However, due to 3D data's sparsity and unorderedness, specially designed networks and modules are needed to process this type of data. Attention mechanism has achieved impressive performance in diverse computer vision tasks; however, it is unclear how attention modules would affect the performance of 3D point cloud object detection and what sort of attention modules could fit with the inherent properties of 3D data. This work investigates the role of the attention mechanism in 3D point cloud object detection and provides insights into the potential of different attention modules. To achieve that, we comprehensively investigate classical 2D attentions, novel 3D attentions, including the latest point cloud transformers on SUN RGB-D and ScanNetV2 datasets. Based on the detailed experiments and analysis, we conclude the effects of different attention modules. This paper is expected to serve as a reference source for benefiting attention-embedded 3D point cloud object detection. The code and trained models are available at: https://github.com/ShiQiu0419/attentions_in_3D_detection.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 43 of its 54 references that are in the map. First posted on arXiv 2 Aug 2021.

Builds on

43 of 54 references.

References · 43

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2017Mask R-CNNcited by 7,259
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2017Squeeze-and-Excitation Networkscited by 4,763
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  8. 2015Fast R-CNNcited by 2,930
  9. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  10. 2017Non-local Neural Networkscited by 2,290
  11. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  12. 2020Point Transformercited by 1,462
31 more
  1. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  2. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  3. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  4. 2021Transformers in Vision: A Surveycited by 1,009
  5. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  6. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  7. 2020PCT: Point cloud transformercited by 730
  8. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  9. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  10. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  11. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  12. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  13. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  14. 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
  15. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  16. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  17. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  18. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  19. 2020Deep Continuous Fusion for Multi-Sensor 3D Object Detectioncited by 263
  20. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  21. 2019Real Image Denoising with Feature Attentioncited by 176
  22. 2017PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimationcited by 170
  23. 2019MVX-Net: Multimodal VoxelNet for 3D Object Detectioncited by 162
  24. 2019Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detectioncited by 124
  25. 2020ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votescited by 119
  26. 2018Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Networkcited by 100
  27. 2020MLCVNet: Multi-Level Context VoteNet for 3D Object Detectioncited by 80
  28. 2020HDNET: Exploiting HD Maps for 3D Object Detectioncited by 78
  29. 2021Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusioncited by 71
  30. 2020Dense-Resolution Network for Point Cloud Classification and Segmentationcited by 45
  31. 2019Point Attention Network for Semantic Segmentation of 3D Point Cloudscited by 29

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 4; 2023: 1; 2024: 2; 2025: 1.

10 papers.

  1. 2022Visual Attention Methods in Deep Learning: An In-Depth Surveycited by 37
  2. 2021PU-Transformer: Point Cloud Upsampling Transformercited by 32
  3. 2022Transformers in 3D Point Clouds: A Surveycited by 31
  4. 2021PartGlot: Learning Shape Part Segmentation from Language Reference Gamescited by 30
  5. 2024MUFASA: Multi-View Fusion and Adaptation Network with Spatial Awareness for Radar Object Detectioncited by 13
  6. 2022PointCaM: Cut-and-Mix for Open-Set Point Cloud Learningcited by 11
  7. 2022Energy-Based Residual Latent Transport for Unsupervised Point Cloud Completioncited by 9
  8. 2023Graph Structure from Point Clouds: Geometric Attention is All You Needcited by 2
  9. 2024KGpose: Keypoint-Graph Driven End-to-End Multi-Object 6D Pose Estimation via Point-Wise Pose Votingcited by 0
  10. 2025Point upsampling networks for single-photon sensingcited by 0