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

arXiv: https://arxiv.org/abs/2007.13373 · HTML: https://mlsanity.com/paper/2007.13373/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2020.

## Built on by (most cited first, 30 of 34)

- [FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism](https://mlsanity.com/paper/2103.07054/) (2021)
- [Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving](https://mlsanity.com/paper/2303.11040/) (2023)
- [Regularization Strategy for Point Cloud via Rigidly Mixed Sample](https://mlsanity.com/paper/2102.01929/) (2021)
- [Transformation-Equivariant 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/2211.11962/) (2022)
- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection](https://mlsanity.com/paper/2307.11477/) (2023)
- [Is Your HD Map Constructor Reliable under Sensor Corruptions?](https://mlsanity.com/paper/2406.12214/) (2024)
- [Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2308.12113/) (2023)
- [A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attacks](https://mlsanity.com/paper/2212.10230/) (2022)
- [A Survey of Label-Efficient Deep Learning for 3D Point Clouds](https://mlsanity.com/paper/2305.19812/) (2023)
- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [Exploring Geometric Consistency for Monocular 3D Object Detection](https://mlsanity.com/paper/2104.05858/) (2021)
- [Instant Domain Augmentation for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2303.14378/) (2023)
- [Pattern-Aware Data Augmentation for LiDAR 3D Object Detection](https://mlsanity.com/paper/2112.00050/) (2021)
- [3D Data Augmentation for Driving Scenes on Camera](https://mlsanity.com/paper/2303.10340/) (2023)
- [Common Corruption Robustness of Point Cloud Detectors: Benchmark and Enhancement](https://mlsanity.com/paper/2210.05896/) (2022)
- [What Really Matters for Robust Multi-Sensor HD Map Construction?](https://mlsanity.com/paper/2507.01484/) (2025)
- [LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations](https://mlsanity.com/paper/2210.13488/) (2022)
- [PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds](https://mlsanity.com/paper/2210.13428/) (2022)
- [Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detection](https://mlsanity.com/paper/2305.12853/) (2023)
- [Domain Generalization of 3D Object Detection by Density-Resampling](https://mlsanity.com/paper/2311.10845/) (2023)
- [Context-Aware Data Augmentation for LIDAR 3D Object Detection](https://mlsanity.com/paper/2211.10850/) (2022)
- [GraVoS: Voxel Selection for 3D Point-Cloud Detection](https://mlsanity.com/paper/2208.08780/) (2022)
- [Learning Object-level Point Augmentor for Semi-supervised 3D Object Detection](https://mlsanity.com/paper/2212.09273/) (2022)
- [DR.CPO: Diversified and Realistic 3D Augmentation via Iterative Construction, Random Placement, and HPR Occlusion](https://mlsanity.com/paper/2303.12743/) (2023)
- [GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2503.08639/) (2025)
- [On Automatic Data Augmentation for 3D Point Cloud Classification](https://mlsanity.com/paper/2112.06029/) (2021)
- [Category-Level 6D Object Pose Estimation with Flexible Vector-Based Rotation Representation](https://mlsanity.com/paper/2212.04632/) (2022)
- [Improving Generalization Ability for 3D Object Detection by Learning Sparsity-invariant Features](https://mlsanity.com/paper/2502.02322/) (2025)
- [LiDARDraft: Generating LiDAR Point Cloud from Versatile Inputs](https://mlsanity.com/paper/2512.20105/) (2025)

## 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