mlsanityData to 7 Oct 2026

Part-Aware Data Augmentation for 3D Object Detection in Point Cloud

arXiv 2007.13373 ↗First posted 27 Jul 2020cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

Data augmentation has greatly contributed to improving the performance in image recognition tasks, and a lot of related studies have been conducted. However, data augmentation on 3D point cloud data has not been much explored. 3D label has more sophisticated and rich structural information than the 2D label, so it enables more diverse and effective data augmentation. In this paper, we propose part-aware data augmentation (PA-AUG) that can better utilize rich information of 3D label to enhance the performance of 3D object detectors. PA-AUG divides objects into partitions and stochastically applies five augmentation methods to each local region. It is compatible with existing point cloud data augmentation methods and can be used universally regardless of the detector's architecture. PA-AUG has improved the performance of state-of-the-art 3D object detector for all classes of the KITTI dataset and has the equivalent effect of increasing the train data by about 2.5×. We also show that PA-AUG not only increases performance for a given dataset but also is robust to corrupted data. The code is available at https://github.com/sky77764/pa-aug.pytorch

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 11; 2023: 9; 2024: 3; 2025: 6.

34 papers.

Sort:

By area:

  1. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  2. 2023Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Drivingcited by 112
  3. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  4. 2022Transformation-Equivariant 3D Object Detection for Autonomous Drivingcited by 52
  5. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 30
  6. 2023SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detectioncited by 30
  7. 2024Is Your HD Map Constructor Reliable under Sensor Corruptions?cited by 28
  8. 2023Advancements in Point Cloud Data Augmentation for Deep Learning: A Surveycited by 24
  9. 2022A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attackscited by 22
  10. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  11. 2024A Survey on Mixup Augmentations and Beyondcited by 18
  12. 2021Exploring Geometric Consistency for Monocular 3D Object Detectioncited by 17
22 more
  1. 2023Instant Domain Augmentation for LiDAR Semantic Segmentationcited by 16
  2. 2021Pattern-Aware Data Augmentation for LiDAR 3D Object Detectioncited by 15
  3. 20233D Data Augmentation for Driving Scenes on Cameracited by 12
  4. 2022Common Corruption Robustness of Point Cloud Detectors: Benchmark and Enhancementcited by 9
  5. 2025What Really Matters for Robust Multi-Sensor HD Map Construction?cited by 9
  6. 2022LidarAugment: Searching for Scalable 3D LiDAR Data Augmentationscited by 8
  7. 2022PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Cloudscited by 7
  8. 2023Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detectioncited by 7
  9. 2023Domain Generalization of 3D Object Detection by Density-Resamplingcited by 6
  10. 2022Context-Aware Data Augmentation for LIDAR 3D Object Detectioncited by 5
  11. 2022GraVoS: Voxel Selection for 3D Point-Cloud Detectioncited by 3
  12. 2022Learning Object-level Point Augmentor for Semi-supervised 3D Object Detectioncited by 2
  13. 2023DR.CPO: Diversified and Realistic 3D Augmentation via Iterative Construction, Random Placement, and HPR Occlusioncited by 2
  14. 2025GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detectioncited by 2
  15. 2021On Automatic Data Augmentation for 3D Point Cloud Classificationcited by 1
  16. 2022Category-Level 6D Object Pose Estimation with Flexible Vector-Based Rotation Representationcited by 1
  17. 2025Improving Generalization Ability for 3D Object Detection by Learning Sparsity-invariant Featurescited by 1
  18. 2025LiDARDraft: Generating LiDAR Point Cloud from Versatile Inputscited by 1
  19. 2022Resolving Class Imbalance for LiDAR-based Object Detector by Dynamic Weight Average and Contextual Ground Truth Samplingcited by 0
  20. 2024SGCCNet: Single-Stage 3D Object Detector With Saliency-Guided Data Augmentation and Confidence Correction Mechanismcited by 0
  21. 2025A Data-Centric Approach to 3D Semantic Segmentation of Railway Scenescited by 0
  22. 2025Which LiDAR scanning pattern is better for roadside perception: Repetitive or Non-repetitive?cited by 0