mlsanityData to 7 Oct 2026

LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection

arXiv 2203.14956 ↗First posted 28 Mar 2022cs.CV cs.ROcited by 54

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose the LiDAR Distillation to bridge the domain gap induced by different LiDAR beams for 3D object detection. In many real-world applications, the LiDAR points used by mass-produced robots and vehicles usually have fewer beams than that in large-scale public datasets. Moreover, as the LiDARs are upgraded to other product models with different beam amount, it becomes challenging to utilize the labeled data captured by previous versions' high-resolution sensors. Despite the recent progress on domain adaptive 3D detection, most methods struggle to eliminate the beam-induced domain gap. We find that it is essential to align the point cloud density of the source domain with that of the target domain during the training process. Inspired by this discovery, we propose a progressive framework to mitigate the beam-induced domain shift. In each iteration, we first generate low-beam pseudo LiDAR by downsampling the high-beam point clouds. Then the teacher-student framework is employed to distill rich information from the data with more beams. Extensive experiments on Waymo, nuScenes and KITTI datasets with three different LiDAR-based detectors demonstrate the effectiveness of our LiDAR Distillation. Notably, our approach does not increase any additional computation cost for inference.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). Builds on 47 of its 59 references that are in the map. First posted on arXiv 28 Mar 2022.

Builds on

47 of 59 references.

References · 47

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  4. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  5. 2014FitNets: Hints for Thin Deep Netscited by 1,619
  6. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  7. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  8. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  9. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  10. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  11. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  12. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
35 more
  1. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  2. 2019Similarity-Preserving Knowledge Distillationcited by 507
  3. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
  4. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  5. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  6. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  7. 2019A Comprehensive Overhaul of Feature Distillationcited by 341
  8. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  9. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  10. 2018Strong-Weak Distribution Alignment for Adaptive Object Detectioncited by 269
  11. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 231
  12. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  13. 2019Lightweight Image Super-Resolution with Information Multi-distillation Networkcited by 227
  14. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 222
  15. 2019Distilling Object Detectors with Fine-grained Feature Imitationcited by 188
  16. 2020LMSCNet: Lightweight Multiscale 3D Semantic Completioncited by 187
  17. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 158
  18. 2017Asymmetric Tri-training for Unsupervised Domain Adaptationcited by 152
  19. 2020Train in Germany, Test in The USA: Making 3D Object Detectors Generalizecited by 150
  20. 2018Large scale distributed neural network training through online distillationcited by 144
  21. 2020Exploring Categorical Regularization for Domain Adaptive Object Detectioncited by 130
  22. 2019xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 129
  23. 2020Harmonizing Transferability and Discriminability for Adapting Object Detectorscited by 125
  24. 2020Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Cloudscited by 116
  25. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  26. 2021Distilling Object Detectors via Decoupled Featurescited by 105
  27. 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 93
  28. 2020Cross-domain Object Detection through Coarse-to-Fine Feature Adaptationcited by 82
  29. 2021Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistencycited by 63
  30. 2020Spatial Attention Pyramid Network for Unsupervised Domain Adaptationcited by 56
  31. 2020SF-UDA3D: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detectioncited by 25
  32. 2018Quantization Mimic: Towards Very Tiny CNN for Object Detectioncited by 20
  33. 2021Uncertainty-aware Mean Teacher for Source-free Unsupervised Domain Adaptive 3D Object Detectioncited by 18
  34. 2017Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistencycited by 14
  35. 2021Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detectioncited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 18; 2024: 23; 2025: 7; 2026: 3.

54 papers.

Sort:

  1. 2023Robo3D: Towards Robust and Reliable 3D Perception against Corruptionscited by 128
  2. 2024A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlookcited by 65
  3. 2023Uni3D: A Unified Baseline for Multi-dataset 3D Object Detectioncited by 39
  4. 2023Density-Insensitive Unsupervised Domain Adaption on 3D Object Detectioncited by 31
  5. 2023X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detectioncited by 28
  6. 2023Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labelingcited by 28
  7. 2024CRKD: Enhanced Camera-Radar Object Detection with Cross-modality Knowledge Distillationcited by 27
  8. 2024Is Your LiDAR Placement Optimized for 3D Scene Understanding?cited by 25
  9. 2024Multi-Space Alignments Towards Universal LiDAR Segmentationcited by 24
  10. 2023Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detectioncited by 21
  11. 2023SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptationcited by 21
  12. 2023AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Datasetcited by 21
38 more
  1. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  2. 2023Benchmarking the Robustness of LiDAR Semantic Segmentation Modelscited by 18
  3. 2023MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detectioncited by 14
  4. 2024Event-guided Low-light Video Semantic Segmentationcited by 14
  5. 2023ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulationcited by 13
  6. 2024Unified Domain Generalization and Adaptation for Multi-View 3D Object Detectioncited by 13
  7. 2023MS3D: Leveraging Multiple Detectors for Unsupervised Domain Adaptation in 3D Object Detectioncited by 12
  8. 2024CrackNex: a Few-shot Low-light Crack Segmentation Model Based on Retinex Theory for UAV Inspectionscited by 12
  9. 2024UADA3D: Unsupervised Adversarial Domain Adaptation for 3D Object Detection with Sparse LiDAR and Large Domain Gapscited by 12
  10. 2024PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understandingcited by 11
  11. 2022Viewer-Centred Surface Completion for Unsupervised Domain Adaptation in 3D Object Detectioncited by 10
  12. 2024An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domainscited by 10
  13. 2023GeoAdapt: Self-Supervised Test-Time Adaptation in LiDAR Place Recognition Using Geometric Priorscited by 8
  14. 2022Paint and Distill: Boosting 3D Object Detection with Semantic Passing Networkcited by 7
  15. 2023Rethinking LiDAR Domain Generalization: Single Source as Multiple Density Domainscited by 7
  16. 2024Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Cloudscited by 7
  17. 2024Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detectioncited by 7
  18. 2023Practical Collaborative Perception: A Framework for Asynchronous and Multi-Agent 3D Object Detectioncited by 6
  19. 2024MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detectioncited by 6
  20. 2024STAL3D: Unsupervised Domain Adaptation for 3D Object Detection via Collaborating Self-Training and Adversarial Learningcited by 6
  21. 2024Segment, Lift and Fit: Automatic 3D Shape Labeling from 2D Promptscited by 6
  22. 2023Offline-to-Online Knowledge Distillation for Video Instance Segmentationcited by 5
  23. 2022SAILOR: Scaling Anchors via Insights into Latent Object Representationcited by 4
  24. 2024Detect Closer Surfaces that can be Seen: New Modeling and Evaluation in Cross-domain 3D Object Detectioncited by 4
  25. 2024Learning 3D Perception from Others' Predictionscited by 4
  26. 2024DALI: Domain Adaptive LiDAR Object Detection via Distribution-level and Instance-level Pseudo Label Denoisingcited by 4
  27. 2024LEROjD: Lidar Extended Radar-Only Object Detectioncited by 3
  28. 2024Uni2Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D Detectioncited by 3
  29. 2025Reflectance Prediction-based Knowledge Distillation for Robust 3D Object Detection in Compressed Point Cloudscited by 3
  30. 2024Revisiting Cross-Domain Problem for LiDAR-based 3D Object Detectioncited by 2
  31. 2025GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detectioncited by 2
  32. 2025Improving Multimodal Distillation for 3D Semantic Segmentation under Domain Shiftcited by 2
  33. 2023Semantic Segmentation on 3D Point Clouds with High Density Variationscited by 1
  34. 2024Semi-Supervised Domain Adaptation Using Target-Oriented Domain Augmentation for 3D Object Detectioncited by 1
  35. 2025Improving Generalization Ability for 3D Object Detection by Learning Sparsity-invariant Featurescited by 1
  36. 2026RESOLVE: A Multi-Resolution and Multi-Modal Dataset for Roadside Cooperative Perceptioncited by 1
  37. 2024Finetuning Pre-trained Model with Limited Data for LiDAR-based 3D Object Detection by Bridging Domain Gapscited by 0
  38. 2025An Investigation of Beam Density on LiDAR Object Detection Performancecited by 0

50 most cited of 54 All 54 (JSON)