mlsanityData to 14 Oct 2026

Sample-adaptive Augmentation for Point Cloud Recognition Against Real-world Corruptions

arXiv 2309.10431 ↗First posted 19 Sep 2023cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Robust 3D perception under corruption has become an essential task for the realm of 3D vision. While current data augmentation techniques usually perform random transformations on all point cloud objects in an offline way and ignore the structure of the samples, resulting in over-or-under enhancement. In this work, we propose an alternative to make sample-adaptive transformations based on the structure of the sample to cope with potential corruption via an auto-augmentation framework, named as AdaptPoint. Specially, we leverage a imitator, consisting of a Deformation Controller and a Mask Controller, respectively in charge of predicting deformation parameters and producing a per-point mask, based on the intrinsic structural information of the input point cloud, and then conduct corruption simulations on top. Then a discriminator is utilized to prevent the generation of excessive corruption that deviates from the original data distribution. In addition, a perception-guidance feedback mechanism is incorporated to guide the generation of samples with appropriate difficulty level. Furthermore, to address the paucity of real-world corrupted point cloud, we also introduce a new dataset ScanObjectNN-C, that exhibits greater similarity to actual data in real-world environments, especially when contrasted with preceding CAD datasets. Experiments show that our method achieves state-of-the-art results on multiple corruption benchmarks, including ModelNet-C, our ScanObjectNN-C, and ShapeNet-C.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 32 of its 39 references that are in the map. First posted on arXiv 19 Sep 2023.

Builds on

32 of 39 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  9. 2020Point Transformercited by 1,470
  10. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  11. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  12. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
20 more
  1. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  2. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 436
  3. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  4. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  5. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  6. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  7. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  8. 2018Generating 3D Adversarial Point Cloudscited by 144
  9. 2018PointCloud Saliency Mapscited by 112
  10. 2020PointMixup: Augmentation for Point Cloudscited by 104
  11. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 89
  12. 2020Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloudcited by 71
  13. 2022Benchmarking and Analyzing Point Cloud Classification under Corruptionscited by 70
  14. 2020PointAugment: an Auto-Augmentation Framework for Point Cloud Classificationcited by 65
  15. 2019Adversarial Attack and Defense on Point Setscited by 63
  16. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  17. 2020LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networkscited by 55
  18. 2020IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restorationcited by 46
  19. 2021Point Cloud Augmentation with Weighted Local Transformationscited by 39
  20. 2021PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Cloudscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 0; 2026: 3.

6 papers.

  1. 2026Utonia: Toward One Encoder for All Point Cloudscited by 21
  2. 2024GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistencycited by 18
  3. 2024Target-Guided Adversarial Point Cloud Transformer Towards Recognition Against Real-world Corruptionscited by 2
  4. 20243D Adaptive Structural Convolution Network for Domain-Invariant Point Cloud Recognitioncited by 0
  5. 2026Structure-First Point Cloud Learning with Mapper Region Graphscited by 0
  6. 2026Point-Selection Fine-Tuning Framework for Robust Point Cloud Classificationcited by 0