mlsanityData to 7 Oct 2026

CRKD: Enhanced Camera-Radar Object Detection with Cross-modality Knowledge Distillation

arXiv 2403.19104 ↗First posted 28 Mar 2024cs.CV cs.ROcited by 27

Not on the map. Why?

Abstract (arXiv)

In the field of 3D object detection for autonomous driving, LiDAR-Camera (LC) fusion is the top-performing sensor configuration. Still, LiDAR is relatively high cost, which hinders adoption of this technology for consumer automobiles. Alternatively, camera and radar are commonly deployed on vehicles already on the road today, but performance of Camera-Radar (CR) fusion falls behind LC fusion. In this work, we propose Camera-Radar Knowledge Distillation (CRKD) to bridge the performance gap between LC and CR detectors with a novel cross-modality KD framework. We use the Bird's-Eye-View (BEV) representation as the shared feature space to enable effective knowledge distillation. To accommodate the unique cross-modality KD path, we propose four distillation losses to help the student learn crucial features from the teacher model. We present extensive evaluations on the nuScenes dataset to demonstrate the effectiveness of the proposed CRKD framework. The project page for CRKD is https://song-jingyu.github.io/CRKD.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 56 of its 72 references that are in the map. First posted on arXiv 28 Mar 2024.

Builds on

56 of 72 references.

References · 56

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  5. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  6. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  7. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  8. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  9. 2022Planning-oriented Autonomous Drivingcited by 1,068
  10. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  11. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  12. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
38 more
  1. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  2. 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
  3. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
  4. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  5. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  6. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 334
  7. 2022FUTR3D: A Unified Sensor Fusion Framework for 3D Detectioncited by 194
  8. 20203D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detectioncited by 176
  9. 2019MVX-Net: Multimodal VoxelNet for 3D Object Detectioncited by 162
  10. 2020CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detectioncited by 159
  11. 2020CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detectioncited by 147
  12. 2022Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Datacited by 126
  13. 2022DeepInteraction: 3D Object Detection via Modality Interactioncited by 125
  14. 2021FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detectioncited by 92
  15. 2023CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perceptioncited by 81
  16. 2021LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detectorcited by 69
  17. 2022MonoDistill: Learning Spatial Features for Monocular 3D Object Detectioncited by 68
  18. 2022CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformercited by 66
  19. 2022BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detectioncited by 66
  20. 2021Object DGCNN: 3D Object Detection using Dynamic Graphscited by 58
  21. 2022Waymo Open Dataset: Panoramic Video Panoptic Segmentationcited by 57
  22. 2022LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detectioncited by 54
  23. 2023Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Trackingcited by 54
  24. 2022Voxel Field Fusion for 3D Object Detectioncited by 50
  25. 2020RadarNet: Exploiting Radar for Robust Perception of Dynamic Objectscited by 48
  26. 2022Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detectioncited by 48
  27. 2022Bridging the View Disparity Between Radar and Camera Features for Multi-modal Fusion 3D Object Detectioncited by 46
  28. 2023UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye Viewcited by 43
  29. 2023DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillationcited by 41
  30. 2022MotionSC: Data Set and Network for Real-Time Semantic Mapping in Dynamic Environmentscited by 40
  31. 2023EA-LSS: Edge-aware Lift-splat-shot Framework for 3D BEV Object Detectioncited by 38
  32. 2022TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learningcited by 37
  33. 2022PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detectioncited by 33
  34. 2022Towards Efficient 3D Object Detection with Knowledge Distillationcited by 29
  35. 2023MVFusion: Multi-View 3D Object Detection with Semantic-aligned Radar and Camera Fusioncited by 29
  36. 2023X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detectioncited by 28
  37. 2023RCM-Fusion: Radar-Camera Multi-Level Fusion for 3D Object Detectioncited by 23
  38. 2023HVDetFusion: A Simple and Robust Camera-Radar Fusion Frameworkcited by 18

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 12; 2026: 8.

27 papers.

Sort:

By area:

  1. 2025Multimodal Fusion and Vision-Language Models: A Survey for Robot Visioncited by 37
  2. 2024LiCROcc: Teach Radar for Accurate Semantic Occupancy Prediction using LiDAR and Cameracited by 18
  3. 2024CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for 3D Object Detectioncited by 18
  4. 2025RadarSplat: Radar Gaussian Splatting for High-Fidelity Data Synthesis and 3D Reconstruction of Autonomous Driving Scenescited by 15
  5. 2024MemFusionMap: Working Memory Fusion for Online Vectorized HD Map Constructioncited by 9
  6. 2024Radar and Camera Fusion for Object Detection and Tracking: A Comprehensive Surveycited by 9
  7. 2024SpaRC: Sparse Radar-Camera Fusion for 3D Object Detectioncited by 8
  8. 2024UniBEVFusion: Unified Radar-Vision BEVFusion for 3D Object Detectioncited by 7
  9. 2024LiRCDepth: Lightweight Radar-Camera Depth Estimation via Knowledge Distillation and Uncertainty Guidancecited by 5
  10. 2025Resource-Efficient Beam Prediction in mmWave Communications with Multimodal Realistic Simulation Frameworkcited by 5
  11. 2025Distilling Cross-Modal Knowledge via Feature Disentanglementcited by 5
  12. 2025Integrating Multi-Modal Sensors: A Review of Fusion Techniques for Intelligent Vehiclescited by 3
15 more
  1. 2025RCTDistill: Cross-Modal Knowledge Distillation Framework for Radar-Camera 3D Object Detection with Temporal Fusioncited by 3
  2. 2025RISE: Single Static Radar-based Indoor Scene Understandingcited by 2
  3. 2025KD360-VoxelBEV: LiDAR and 360-degree Camera Cross Modality Knowledge Distillation for Bird's-Eye-View Segmentationcited by 2
  4. 2025Enhanced 3D Object Detection via Diverse Feature Representations of 4D Radar Tensorcited by 1
  5. 2026MolSight: Molecular Property Prediction with Imagescited by 1
  6. 2025Information-Theoretic Criteria for Knowledge Distillation in Multimodal Learningcited by 0
  7. 2025PEFT-DML: Parameter-Efficient Fine-Tuning Deep Metric Learning for Robust Multi-Modal 3D Object Detection in Autonomous Drivingcited by 0
  8. 2025IMKD: Intensity-Aware Multi-Level Knowledge Distillation for Camera-Radar Fusioncited by 0
  9. 2026SkeFi: Cross-Modal Knowledge Transfer for Wireless Skeleton-Based Action Recognitioncited by 0
  10. 2026CD-FKD: Cross-Domain Feature Knowledge Distillation for Robust Single-Domain Generalization in Object Detectioncited by 0
  11. 2026CLLAP: Contrastive Learning-based LiDAR-Augmented Pretraining for Enhanced Radar-Camera Fusioncited by 0
  12. 2026Control Your Queries: Heterogeneous Query Interaction for Camera-Radar Fusioncited by 0
  13. 2026CRISP: A Spatiotemporal Camera-Radar Backbone for Driving via Forecasting-Based World-Model Pretrainingcited by 0
  14. 2026RAF: Reliability-Aware Fusion of Camera, LiDAR, and 4D RADAR for Robust 3D Object Detection in Adverse Weathercited by 0
  15. 2026RLG-TPV: Radar- and LiDAR-Guided Tri-Perspective View Fusion for Camera-Radar 3D Object Detectioncited by 0