mlsanityData to 7 Oct 2026

DR.CPO: Diversified and Realistic 3D Augmentation via Iterative Construction, Random Placement, and HPR Occlusion

arXiv 2303.12743 ↗First posted 20 Mar 2023cs.CV cs.AI cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

In autonomous driving, data augmentation is commonly used for improving 3D object detection. The most basic methods include insertion of copied objects and rotation and scaling of the entire training frame. Numerous variants have been developed as well. The existing methods, however, are considerably limited when compared to the variety of the real world possibilities. In this work, we develop a diversified and realistic augmentation method that can flexibly construct a whole-body object, freely locate and rotate the object, and apply self-occlusion and external-occlusion accordingly. To improve the diversity of the whole-body object construction, we develop an iterative method that stochastically combines multiple objects observed from the real world into a single object. Unlike the existing augmentation methods, the constructed objects can be randomly located and rotated in the training frame because proper occlusions can be reflected to the whole-body objects in the final step. Finally, proper self-occlusion at each local object level and external-occlusion at the global frame level are applied using the Hidden Point Removal (HPR) algorithm that is computationally efficient. HPR is also used for adaptively controlling the point density of each object according to the object's distance from the LiDAR. Experiment results show that the proposed DR.CPO algorithm is data-efficient and model-agnostic without incurring any computational overhead. Also, DR.CPO can improve mAP performance by 2.08% when compared to the best 3D detection result known for KITTI dataset. The code is available at https://github.com/SNU-DRL/DRCPO.git

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 35 of its 49 references that are in the map. First posted on arXiv 20 Mar 2023.

Builds on

35 of 49 references.

References · 35

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  3. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  4. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  5. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  6. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  7. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  8. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  9. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  10. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  11. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  12. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
23 more
  1. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  2. 2020Deep Continuous Fusion for Multi-Sensor 3D Object Detectioncited by 263
  3. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  4. 20203D Object Detection with Pointformercited by 194
  5. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  6. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
  7. 2019IoU Loss for 2D/3D Object Detectioncited by 128
  8. 2019Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detectioncited by 124
  9. 2017Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenescited by 122
  10. 2020CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloudcited by 107
  11. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
  12. 2019Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspotscited by 84
  13. 2016Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networkscited by 72
  14. 2019What You See is What You Get: Exploiting Visibility for 3D Object Detectioncited by 69
  15. 2021Behind the Curtain: Learning Occluded Shapes for 3D Object Detectioncited by 58
  16. 2018A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Drivingcited by 54
  17. 2019StarNet: Targeted Computation for Object Detection in Point Cloudscited by 46
  18. 2018Augmented LiDAR Simulator for Autonomous Drivingcited by 41
  19. 2020Improving 3D Object Detection through Progressive Population Based Augmentationcited by 41
  20. 2020Part-Aware Data Augmentation for 3D Object Detection in Point Cloudcited by 34
  21. 2020Quantifying Data Augmentation for LiDAR based 3D Object Detectioncited by 18
  22. 2021Pattern-Aware Data Augmentation for LiDAR 3D Object Detectioncited by 15
  23. 2019Patch Refinement -- Localized 3D Object Detectioncited by 7

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentationcited by 2
  2. 2025TransBridge: Boost 3D Object Detection by Scene-Level Completion with Transformer Decodercited by 0