mlsanityData to 14 Oct 2026

What Can be Seen is What You Get: Structure Aware Point Cloud Augmentation

arXiv 2206.09664 ↗First posted 20 Jun 2022cs.CV cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

To train a well performing neural network for semantic segmentation, it is crucial to have a large dataset with available ground truth for the network to generalize on unseen data. In this paper we present novel point cloud augmentation methods to artificially diversify a dataset. Our sensor-centric methods keep the data structure consistent with the lidar sensor capabilities. Due to these new methods, we are able to enrich low-value data with high-value instances, as well as create entirely new scenes. We validate our methods on multiple neural networks with the public SemanticKITTI dataset and demonstrate that all networks improve compared to their respective baseline. In addition, we show that our methods enable the use of very small datasets, saving annotation time, training time and the associated costs.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 20 of its 30 references that are in the map. First posted on arXiv 20 Jun 2022.

Builds on

20 of 30 references.

References · 20

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  3. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  4. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  5. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  6. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 223
  7. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  8. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  9. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  10. 2020Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentationcited by 112
  11. 2021Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentationcited by 107
  12. 2020PointMixup: Augmentation for Point Cloudscited by 104
8 more
  1. 2020AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentationcited by 87
  2. 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
  3. 20203D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentationcited by 58
  4. 2021VPFNet: Improving 3D Object Detection with Virtual Point based LiDAR and Stereo Data Fusioncited by 48
  5. 2020Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental Studycited by 33
  6. 2021Pattern-Aware Data Augmentation for LiDAR 3D Object Detectioncited by 15
  7. 2018OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillationcited by 5
  8. 2019Multimodal 3D Object Detection from Simulated Pretrainingcited by 4

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 2.

6 papers.

  1. 2023Advancements in Point Cloud Data Augmentation for Deep Learning: A Surveycited by 24
  2. 2023Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detectioncited by 7
  3. 2024Text3DAug -- Prompted Instance Augmentation for LiDAR Perceptioncited by 4
  4. 2023MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistencycited by 3
  5. 2022Fake it, Mix it, Segment it: Bridging the Domain Gap Between Lidar Sensorscited by 2
  6. 2024ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Onlycited by 1