mlsanityData to 7 Oct 2026

Task-Aware Sampling Layer for Point-Wise Analysis

arXiv 2107.04291 ↗First posted 9 Jul 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Sampling, grouping, and aggregation are three important components in the multi-scale analysis of point clouds. In this paper, we present a novel data-driven sampler learning strategy for point-wise analysis tasks. Unlike the widely used sampling technique, Farthest Point Sampling (FPS), we propose to learn sampling and downstream applications jointly. Our key insight is that uniform sampling methods like FPS are not always optimal for different tasks: sampling more points around boundary areas can make the point-wise classification easier for segmentation. Towards this end, we propose a novel sampler learning strategy that learns sampling point displacement supervised by task-related ground truth information and can be trained jointly with the underlying tasks. We further demonstrate our methods in various point-wise analysis tasks, including semantic part segmentation, point cloud completion, and keypoint detection. Our experiments show that jointly learning of the sampler and task brings better performance than using FPS in various point-based networks.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 41 of its 59 references that are in the map. First posted on arXiv 9 Jul 2021.

Builds on

41 of 59 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  8. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  9. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  10. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  11. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  12. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
29 more
  1. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  2. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  3. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  4. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  5. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  6. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  7. 2018PCN: Point Completion Networkcited by 382
  8. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  9. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  10. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  11. 2017Submanifold Sparse Convolutional Networkscited by 223
  12. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  13. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  14. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  15. 2017Pointwise Convolutional Neural Networkscited by 126
  16. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  17. 2018Local Spectral Graph Convolution for Point Set Feature Learningcited by 84
  18. 2019SampleNet: Differentiable Point Cloud Samplingcited by 74
  19. 2018RGCNN: Regularized Graph CNN for Point Cloud Segmentationcited by 70
  20. 2020FPConv: Learning Local Flattening for Point Convolutioncited by 55
  21. 2018A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Drivingcited by 54
  22. 2020Pointfilter: Point Cloud Filtering via Encoder-Decoder Modelingcited by 50
  23. 2020KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotationscited by 50
  24. 2018TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshescited by 45
  25. 2019PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentationcited by 44
  26. 2019A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Imagescited by 37
  27. 2020Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discriminationcited by 31
  28. 2020Skeleton-bridged Point Completion: From Global Inference to Local Adjustmentcited by 23
  29. 2020Learning Part Boundaries from 3D Point Cloudscited by 9

Built on by

Cited by year

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

6 papers.

  1. 2023SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Datacited by 9
  2. 2023A Correct-and-Certify Approach to Self-Supervise Object Pose Estimators via Ensemble Self-Trainingcited by 6
  3. 2024Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Featurescited by 4
  4. 2023Self-supervised Learning for Enhancing Geometrical Modeling in 3D-Aware Generative Adversarial Networkcited by 1
  5. 2022AS-PD: An Arbitrary-Size Downsampling Framework for Point Cloudscited by 0
  6. 2023DSMNet: Deep High-precision 3D Surface Modeling from Sparse Point Cloud Framescited by 0