mlsanityData to 14 Oct 2026

Enhancing Robustness to Noise Corruption for Point Cloud Recognition via Spatial Sorting and Set-Mixing Aggregation Module

arXiv 2407.10806 ↗First posted 15 Jul 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Current models for point cloud recognition demonstrate promising performance on synthetic datasets. However, real-world point cloud data inevitably contains noise, impacting model robustness. While recent efforts focus on enhancing robustness through various strategies, there still remains a gap in comprehensive analyzes from the standpoint of network architecture design. Unlike traditional methods that rely on generic techniques, our approach optimizes model robustness to noise corruption through network architecture design. Inspired by the token-mixing technique applied in 2D images, we propose Set-Mixer, a noise-robust aggregation module which facilitates communication among all points to extract geometric shape information and mitigating the influence of individual noise points. A sorting strategy is designed to enable our module to be invariant to point permutation, which also tackles the unordered structure of point cloud and introduces consistent relative spatial information. Experiments conducted on ModelNet40-C indicate that Set-Mixer significantly enhances the model performance on noisy point clouds, underscoring its potential to advance real-world applicability in 3D recognition and perception tasks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 39 of its 50 references that are in the map. First posted on arXiv 15 Jul 2024.

Builds on

39 of 50 references.

References · 39

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  4. 2020Point Transformercited by 1,470
  5. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  6. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  7. 2020PCT: Point cloud transformercited by 732
  8. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  9. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  10. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 431
  11. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 388
  12. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
27 more
  1. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  2. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  3. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  4. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  5. 2023Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Drivingcited by 114
  6. 2020PointMixup: Augmentation for Point Cloudscited by 104
  7. 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
  8. 2019Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 80
  9. 2022Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptionscited by 80
  10. 2020Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloudcited by 71
  11. 2021PointMixer: MLP-Mixer for Point Cloud Understandingcited by 71
  12. 2022Benchmarking and Analyzing Point Cloud Classification under Corruptionscited by 70
  13. 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
  14. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  15. 2021PointGuard: Provably Robust 3D Point Cloud Classificationcited by 49
  16. 2021Point Cloud Augmentation with Weighted Local Transformationscited by 39
  17. 2022RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 29
  18. 20213D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysiscited by 23
  19. 2022Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusioncited by 8
  20. 20223D Cascade RCNN: High Quality Object Detection in Point Cloudscited by 7
  21. 2023PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restorationcited by 7
  22. 20212D vs. 3D LiDAR-based Person Detection on Mobile Robotscited by 6
  23. 2024Local-consistent Transformation Learning for Rotation-invariant Point Cloud Analysiscited by 6
  24. 2022Rethinking Rotation Invariance with Point Cloud Registrationcited by 5
  25. 2023EPiC: Ensemble of Partial Point Clouds for Robust Classificationcited by 5
  26. 2023Robustifying Point Cloud Networks by Refocusingcited by 2
  27. 2023CSI: Enhancing the Robustness of 3D Point Cloud Recognition against Corruptioncited by 1

Built on by

Not cited yet.