mlsanityData to 7 Oct 2026

Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detection

arXiv 2305.12853 ↗First posted 22 May 2023cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Data and model are the undoubtable two supporting pillars for LiDAR object detection. However, data-centric works have fallen far behind compared with the ever-growing list of fancy new models. In this work, we systematically study the synthesis-based LiDAR data augmentation approach (so-called GT-Aug) which offers maxium controllability over generated data samples. We pinpoint the main shortcoming of existing works is introducing unrealistic LiDAR scan patterns during GT-Aug. In light of this finding, we propose Real-Aug, a synthesis-based augmentation method which prioritizes on generating realistic LiDAR scans. Our method consists a reality-conforming scene composition module which handles the details of the composition and a real-synthesis mixing up training strategy which gradually adapts the data distribution from synthetic data to the real one. To verify the effectiveness of our methods, we conduct extensive ablation studies and validate the proposed Real-Aug on a wide combination of detectors and datasets. We achieve a state-of-the-art 0.744 NDS and 0.702 mAP on nuScenes test set. The code shall be released soon.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 35 of its 44 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

35 of 44 references.

References · 35

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  5. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  6. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  9. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  10. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  11. 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
  12. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
23 more
  1. 2021Voxel Transformer for 3D Object Detectioncited by 247
  2. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  3. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
  4. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  5. 2020LiDARsim: Realistic LiDAR Simulation by Leveraging the Real Worldcited by 137
  6. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  7. 2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
  8. 2018Modeling Visual Context is Key to Augmenting Object Detection Datasetscited by 106
  9. 2020PointMixup: Augmentation for Point Cloudscited by 104
  10. 2022PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detectioncited by 99
  11. 2021Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weathercited by 95
  12. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
  13. 2022LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perceptioncited by 74
  14. 2022LiDAR Snowfall Simulation for Robust 3D Object Detectioncited by 72
  15. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  16. 2019Learning to Generate Synthetic Data via Compositingcited by 52
  17. 2022Patchwork++: Fast and Robust Ground Segmentation Solving Partial Under-Segmentation Using 3D Point Cloudcited by 45
  18. 2020Improving 3D Object Detection through Progressive Population Based Augmentationcited by 41
  19. 2020Part-Aware Data Augmentation for 3D Object Detection in Point Cloudcited by 34
  20. 2021Patchwork: Concentric Zone-based Region-wise Ground Segmentation with Ground Likelihood Estimation Using a 3D LiDAR Sensorcited by 28
  21. 2021Pattern-Aware Data Augmentation for LiDAR 3D Object Detectioncited by 15
  22. 2022What Can be Seen is What You Get: Structure Aware Point Cloud Augmentationcited by 6
  23. 2022Rethinking Dimensionality Reduction in Grid-based 3D Object Detectioncited by 6

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 4; 2025: 2.

7 papers.

  1. 2025Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Modelcited by 17
  2. 2024DAOcc: 3D Object Detection Assisted Multi-Sensor Fusion for 3D Occupancy Predictioncited by 15
  3. 2024Towards Unified 3D Object Detection via Algorithm and Data Unificationcited by 6
  4. 2024Just Add 100 More: Augmenting NeRF-based Pseudo-LiDAR Point Cloud for Resolving Class-imbalance Problemcited by 4
  5. 2023Learned Fusion: 3D Object Detection using Calibration-Free Transformer Feature Fusioncited by 1
  6. 2024SEGT: A General Spatial Expansion Group Transformer for nuScenes Lidar-based Object Detection Taskcited by 1
  7. 2025PTQAT: A Hybrid Parameter-Efficient Quantization Algorithm for 3D Perception Taskscited by 1