mlsanityData to 14 Oct 2026

Global Attention-Guided Dual-Domain Point Cloud Feature Learning for Classification and Segmentation

arXiv 2407.08994 ↗First posted 12 Jul 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Previous studies have demonstrated the effectiveness of point-based neural models on the point cloud analysis task. However, there remains a crucial issue on producing the efficient input embedding for raw point coordinates. Moreover, another issue lies in the limited efficiency of neighboring aggregations, which is a critical component in the network stem. In this paper, we propose a Global Attention-guided Dual-domain Feature Learning network (GAD) to address the above-mentioned issues. We first devise the Contextual Position-enhanced Transformer (CPT) module, which is armed with an improved global attention mechanism, to produce a global-aware input embedding that serves as the guidance to subsequent aggregations. Then, the Dual-domain K-nearest neighbor Feature Fusion (DKFF) is cascaded to conduct effective feature aggregation through novel dual-domain feature learning which appreciates both local geometric relations and long-distance semantic connections. Extensive experiments on multiple point cloud analysis tasks (e.g., classification, part segmentation, and scene semantic segmentation) demonstrate the superior performance of the proposed method and the efficacy of the devised modules.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 58 of its 89 references that are in the map. First posted on arXiv 12 Jul 2024.

Builds on

58 of 89 references.

References · 58

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  6. 2020Point Transformercited by 1,470
  7. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  8. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  9. 2020PCT: Point cloud transformercited by 732
  10. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  11. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  12. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
38 more
  1. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  2. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 436
  3. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 388
  4. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 385
  5. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  6. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 342
  7. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  8. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 310
  9. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  10. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  11. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 239
  12. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  13. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 179
  14. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 167
  15. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 167
  16. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  17. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  18. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  19. 2020MVTN: Multi-View Transformation Network for 3D Shape Recognitioncited by 140
  20. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  21. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 109
  22. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  23. 2023Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Surveycited by 103
  24. 2018Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Networkcited by 100
  25. 2018Recurrent Slice Networks for 3D Segmentation of Point Cloudscited by 82
  26. 2017Deep Projective 3D Semantic Segmentationcited by 81
  27. 2018RGCNN: Regularized Graph CNN for Point Cloud Segmentationcited by 70
  28. 2018VV-Net: Voxel VAE Net with Group Convolutions for Point Cloud Segmentationcited by 64
  29. 2021Adaptive Graph Convolution for Point Cloud Analysiscited by 60
  30. 2021PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysiscited by 58
  31. 2020FPConv: Learning Local Flattening for Point Convolutioncited by 55
  32. 2018A Graph-CNN for 3D Point Cloud Classificationcited by 49
  33. 2020Dense-Resolution Network for Point Cloud Classification and Segmentationcited by 45
  34. 2023NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fieldscited by 44
  35. 2021PVT: Point-Voxel Transformer for Point Cloud Learningcited by 43
  36. 2023Point2Vec for Self-Supervised Representation Learning on Point Cloudscited by 28
  37. 2019Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modelingcited by 25
  38. 2020Cloud Transformers: A Universal Approach To Point Cloud Processing Taskscited by 24

50 most cited of 58 All 58 (JSON)

Built on by

Not cited yet.