mlsanityData to 14 Oct 2026

CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detection

arXiv 2212.00244 ↗First posted 1 Dec 2022cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

Domain adaptation for Cross-LiDAR 3D detection is challenging due to the large gap on the raw data representation with disparate point densities and point arrangements. By exploring domain-invariant 3D geometric characteristics and motion patterns, we present an unsupervised domain adaptation method that overcomes above difficulties. First, we propose the Spatial Geometry Alignment module to extract similar 3D shape geometric features of the same object class to align two domains, while eliminating the effect of distinct point distributions. Second, we present Temporal Motion Alignment module to utilize motion features in sequential frames of data to match two domains. Prototypes generated from two modules are incorporated into the pseudo-label reweighting procedure and contribute to our effective self-training framework for the target domain. Extensive experiments show that our method achieves state-of-the-art performance on cross-device datasets, especially for the datasets with large gaps captured by mechanical scanning LiDARs and solid-state LiDARs in various scenes. Project homepage is at https://github.com/4DVLab/CL3D.git

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 55 of its 68 references that are in the map. First posted on arXiv 1 Dec 2022.

Builds on

55 of 68 references.

References · 55

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  6. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  7. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  8. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  9. 2019Objects as Pointscited by 1,175
  10. 2020Center-based 3D Object Detection and Trackingcited by 1,144
  11. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  12. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
38 more
  1. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
  2. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  3. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 612
  4. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 443
  5. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  6. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 368
  7. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  8. 2016Domain Separation Networkscited by 320
  9. 2018Strong-Weak Distribution Alignment for Adaptive Object Detectioncited by 270
  10. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 243
  11. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 232
  12. 2021PandaSet: Advanced Sensor Suite Dataset for Autonomous Drivingcited by 190
  13. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 159
  14. 2020Train in Germany, Test in The USA: Making 3D Object Detectors Generalizecited by 151
  15. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  16. 2020Gradually Vanishing Bridge for Adversarial Domain Adaptationcited by 130
  17. 2019xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 129
  18. 2018Robust Classification with Convolutional Prototype Learningcited by 123
  19. 2022Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentationcited by 119
  20. 2020Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Cloudscited by 116
  21. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  22. 2019A Robust Learning Approach to Domain Adaptive Object Detectioncited by 109
  23. 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 94
  24. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
  25. 2021Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigationcited by 78
  26. 2021Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentationcited by 76
  27. 2017AutoDIAL: Automatic DomaIn Alignment Layerscited by 75
  28. 2020SSN: Shape Signature Networks for Multi-class Object Detection from Point Cloudscited by 74
  29. 2019Automatic adaptation of object detectors to new domains using self-trainingcited by 66
  30. 2021Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistencycited by 63
  31. 2021Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perceptioncited by 57
  32. 2020Adapting Object Detectors with Conditional Domain Normalizationcited by 55
  33. 2022Enhancing Pseudo Label Quality for Semi-Supervised Domain-Generalized Medical Image Segmentationcited by 51
  34. 2018Boosting Domain Adaptation by Discovering Latent Domainscited by 46
  35. 2019Domain Adaptation for Vehicle Detection from Bird's Eye View LiDAR Point Cloud Datacited by 35
  36. 2022STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenescited by 35
  37. 2021Reference-guided Pseudo-Label Generation for Medical Semantic Segmentationcited by 33
  38. 2018Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptationcited by 29

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 15; 2025: 4; 2026: 4.

27 papers.

Sort:

By area:

  1. 2024RenderWorld: World Model with Self-Supervised 3D Labelcited by 46
  2. 2023SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptationcited by 21
  3. 2024RoboFusion: Towards Robust Multi-Modal 3D Object Detection via SAMcited by 20
  4. 2024LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environmentcited by 20
  5. 2023MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detectioncited by 14
  6. 2024Commonsense Prototype for Outdoor Unsupervised 3D Object Detectioncited by 13
  7. 2024UADA3D: Unsupervised Adversarial Domain Adaptation for 3D Object Detection with Sparse LiDAR and Large Domain Gapscited by 12
  8. 2023Rethinking LiDAR Domain Generalization: Single Source as Multiple Density Domainscited by 7
  9. 2024Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detectioncited by 7
  10. 2024MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detectioncited by 7
  11. 2024LiveHPS++: Robust and Coherent Motion Capture in Dynamic Free Environmentcited by 6
  12. 2024Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptationcited by 6
15 more
  1. 2024DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detectioncited by 5
  2. 2024Learning 3D Perception from Others' Predictionscited by 4
  3. 2024DALI: Domain Adaptive LiDAR Object Detection via Distribution-level and Instance-level Pseudo Label Denoisingcited by 4
  4. 2025LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectivescited by 4
  5. 2025CleverDistiller: Simple and Spatially Consistent Cross-modal Distillationcited by 3
  6. 2024HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenescited by 2
  7. 2024Towards Practical Human Motion Prediction with LiDAR Point Cloudscited by 2
  8. 2023Cross-modal and Cross-domain Knowledge Transfer for Label-free 3D Segmentationcited by 1
  9. 2024Semi-Supervised Domain Adaptation Using Target-Oriented Domain Augmentation for 3D Object Detectioncited by 1
  10. 2025An Investigation of Beam Density on LiDAR Object Detection Performancecited by 0
  11. 2025Domain Adaptation for Different Sensor Configurations in 3D Object Detectioncited by 0
  12. 2026Unified Unsupervised and Sparsely-Supervised 3D Object Detection by Semantic Pseudo-Labeling and Prototype Learningcited by 0
  13. 2026Auto-Labelling-Based Domain Transfer for 3D Object Detection on a Bicycle-Mounted LiDAR Platformcited by 0
  14. 2026SimFuse3D: Source-Guided Target Simulation and Confidence-Guided Multi-Stage Localization Reweighting for Cross-Platform 3D Object Detectioncited by 0
  15. 2026Autonomous Driving Research Requires a Community-Driven Data Paradigmcited by 0