mlsanityData to 7 Oct 2026

Instant Domain Augmentation for LiDAR Semantic Segmentation

arXiv 2303.14378 ↗First posted 25 Mar 2023cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

Despite the increasing popularity of LiDAR sensors, perception algorithms using 3D LiDAR data struggle with the 'sensor-bias problem'. Specifically, the performance of perception algorithms significantly drops when an unseen specification of LiDAR sensor is applied at test time due to the domain discrepancy. This paper presents a fast and flexible LiDAR augmentation method for the semantic segmentation task, called 'LiDomAug'. It aggregates raw LiDAR scans and creates a LiDAR scan of any configurations with the consideration of dynamic distortion and occlusion, resulting in instant domain augmentation. Our on-demand augmentation module runs at 330 FPS, so it can be seamlessly integrated into the data loader in the learning framework. In our experiments, learning-based approaches aided with the proposed LiDomAug are less affected by the sensor-bias issue and achieve new state-of-the-art domain adaptation performances on SemanticKITTI and nuScenes dataset without the use of the target domain data. We also present a sensor-agnostic model that faithfully works on the various LiDAR configurations.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 40 of its 57 references that are in the map. First posted on arXiv 25 Mar 2023.

Builds on

40 of 57 references.

References · 40

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  5. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  6. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  7. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  8. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  9. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  10. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  11. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  12. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
28 more
  1. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  2. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  3. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  4. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  5. 2019Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptationcited by 235
  6. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  7. 2020A2D2: Audi Autonomous Driving Datasetcited by 189
  8. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  9. 2021Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Trackingcited by 165
  10. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  11. 2019xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 129
  12. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  13. 2020Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Cloudscited by 116
  14. 2017No More Discrimination: Cross City Adaptation of Road Scene Segmenterscited by 110
  15. 2020Lidar for Autonomous Driving: The principles, challenges, and trends for automotive lidar and perception systemscited by 100
  16. 2022PolarMix: A General Data Augmentation Technique for LiDAR Point Cloudscited by 74
  17. 2022CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentationcited by 54
  18. 2020KPRNet: Improving projection-based LiDAR semantic segmentationcited by 47
  19. 2021A Survey on Deep Domain Adaptation for LiDAR Perceptioncited by 46
  20. 20213D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detectioncited by 43
  21. 2018Augmented LiDAR Simulator for Autonomous Drivingcited by 41
  22. 2020Improving 3D Object Detection through Progressive Population Based Augmentationcited by 41
  23. 2021ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenationcited by 41
  24. 2022GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentationcited by 35
  25. 2020Part-Aware Data Augmentation for 3D Object Detection in Point Cloudcited by 34
  26. 2020LIBRE: The Multiple 3D LiDAR Datasetcited by 26
  27. 2021Unsupervised Domain Adaptation for LiDAR Panoptic Segmentationcited by 19
  28. 2021Pattern-Aware Data Augmentation for LiDAR 3D Object Detectioncited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 10; 2024: 2; 2025: 2; 2026: 2.

16 papers.

Sort:

By area:

  1. 2023DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detectioncited by 34
  2. 2023Advancements in Point Cloud Data Augmentation for Deep Learning: A Surveycited by 24
  3. 2023SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptationcited by 21
  4. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  5. 2023Pre-training on Synthetic Driving Data for Trajectory Predictioncited by 18
  6. 2024Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weathercited by 14
  7. 2023Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentationcited by 11
  8. 2023GeoAdapt: Self-Supervised Test-Time Adaptation in LiDAR Place Recognition Using Geometric Priorscited by 8
  9. 2025BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenescited by 8
  10. 2023Rethinking LiDAR Domain Generalization: Single Source as Multiple Density Domainscited by 7
  11. 2023Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learningcited by 3
  12. 2025PSA-SSL: Pose and Size-aware Self-Supervised Learning on LiDAR Point Cloudscited by 3
4 more
  1. 2023Paved2Paradise: Cost-Effective and Scalable LiDAR Simulation by Factoring the Real Worldcited by 1
  2. 2026Towards Zero-Shot Point Cloud Registration Across Diverse Scales, Scenes, and Sensor Setupscited by 1
  3. 2026FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Modelcited by 1
  4. 2024Intrinsic Dynamics-Driven Generalizable Scene Representations for Vision-Oriented Decision-Making Applicationscited by 0