mlsanityData to 7 Oct 2026

Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection

arXiv 2211.07171 ↗First posted 14 Nov 2022cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

Leveraging LiDAR-based detectors or real LiDAR point data to guide monocular 3D detection has brought significant improvement, e.g., Pseudo-LiDAR methods. However, the existing methods usually apply non-end-to-end training strategies and insufficiently leverage the LiDAR information, where the rich potential of the LiDAR data has not been well exploited. In this paper, we propose the Cross-Modality Knowledge Distillation (CMKD) network for monocular 3D detection to efficiently and directly transfer the knowledge from LiDAR modality to image modality on both features and responses. Moreover, we further extend CMKD as a semi-supervised training framework by distilling knowledge from large-scale unlabeled data and significantly boost the performance. Until submission, CMKD ranks 1st among the monocular 3D detectors with publications on both KITTI test set and Waymo val set with significant performance gains compared to previous state-of-the-art methods.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 55 of its 70 references that are in the map. First posted on arXiv 14 Nov 2022.

Builds on

55 of 70 references.

References · 55

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  8. 2022A ConvNet for the 2020scited by 3,545
  9. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  10. 2019Searching for MobileNetV3cited by 1,984
  11. 2014FitNets: Hints for Thin Deep Netscited by 1,619
  12. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
38 more
  1. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  2. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  3. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  4. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  5. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  6. 2018Born Again Neural Networkscited by 539
  7. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 532
  8. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  9. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  10. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
  11. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  12. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 326
  13. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  14. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 251
  15. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  16. 2019Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Drivingcited by 188
  17. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 184
  18. 2019Learning Depth-Guided Convolutions for Monocular 3D Object Detectioncited by 169
  19. 2019Stereo R-CNN based 3D Object Detection for Autonomous Drivingcited by 163
  20. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 155
  21. 2020CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detectioncited by 147
  22. 2021Delving into Localization Errors for Monocular 3D Object Detectioncited by 138
  23. 2019Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Drivingcited by 137
  24. 2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
  25. 2019Monocular 3D Object Detection with Pseudo-LiDAR Point Cloudcited by 113
  26. 2021General Instance Distillation for Object Detectioncited by 113
  27. 2020Rethinking Pseudo-LiDAR Representationcited by 109
  28. 2019Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstructioncited by 106
  29. 2021Geometry-based Distance Decomposition for Monocular 3D Object Detectioncited by 83
  30. 2021MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagationcited by 82
  31. 2022MonoDistill: Learning Spatial Features for Monocular 3D Object Detectioncited by 68
  32. 2021Progressive Coordinate Transforms for Monocular 3D Object Detectioncited by 52
  33. 2020Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimationcited by 43
  34. 2021M3DSSD: Monocular 3D Single Stage Object Detectorcited by 39
  35. 2021The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detectioncited by 34
  36. 2019Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Losscited by 30
  37. 2022Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Drivingcited by 30
  38. 2021Lidar Point Cloud Guided Monocular 3D Object Detectioncited by 29

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 18; 2024: 15; 2025: 9; 2026: 5.

48 papers.

Sort:

By area:

  1. 2023ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidancecited by 70
  2. 2022TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learningcited by 37
  3. 2023X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detectioncited by 28
  4. 2024RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Featurescited by 27
  5. 2024CRKD: Enhanced Camera-Radar Object Detection with Cross-modality Knowledge Distillationcited by 27
  6. 2023CoBEV: Elevating Roadside 3D Object Detection with Depth and Height Complementaritycited by 18
  7. 2023MonoLSS: Learnable Sample Selection For Monocular 3D Detectioncited by 18
  8. 2023GeoMIM: Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understandingcited by 17
  9. 2024OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networkscited by 17
  10. 2023Bi-Mapper: Holistic BEV Semantic Mapping for Autonomous Drivingcited by 13
  11. 2023NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localizationcited by 13
  12. 2024Unified Domain Generalization and Adaptation for Multi-View 3D Object Detectioncited by 13
36 more
  1. 2024On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Drivingcited by 10
  2. 2024MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detectioncited by 10
  3. 2024LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object Detectioncited by 9
  4. 2023DualCross: Cross-Modality Cross-Domain Adaptation for Monocular BEV Perceptioncited by 8
  5. 2024Depth-discriminative Metric Learning for Monocular 3D Object Detectioncited by 8
  6. 2025L2COcc: Lightweight Camera-Centric Semantic Scene Completion via Distillation of LiDAR Modelcited by 8
  7. 2024UniVision: A Unified Framework for Vision-Centric 3D Perceptioncited by 7
  8. 2024Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalitiescited by 7
  9. 2023Object-centric Cross-modal Feature Distillation for Event-based Object Detectioncited by 6
  10. 2024Multi-task Learning for Real-time Autonomous Driving Leveraging Task-adaptive Attention Generatorcited by 6
  11. 2023Offline-to-Online Knowledge Distillation for Video Instance Segmentationcited by 5
  12. 2023GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detectioncited by 5
  13. 2023BroadBEV: Collaborative LiDAR-camera Fusion for Broad-sighted Bird's Eye View Map Constructioncited by 4
  14. 2024TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillationcited by 4
  15. 2025Cross-modal Offset-guided Dynamic Alignment and Fusion for Weakly Aligned UAV Object Detectioncited by 3
  16. 2025RCTDistill: Cross-Modal Knowledge Distillation Framework for Radar-Camera 3D Object Detection with Temporal Fusioncited by 3
  17. 2023Weakly Supervised 3D Object Detection with Multi-Stage Generalizationcited by 2
  18. 2024Boosting Online 3D Multi-Object Tracking through Camera-Radar Cross Checkcited by 2
  19. 2025Application of Vision-Language Model to Pedestrians Behavior and Scene Understanding in Autonomous Drivingcited by 2
  20. 2023Towards Fair and Comprehensive Comparisons for Image-Based 3D Object Detectioncited by 1
  21. 2023MonoSKD: General Distillation Framework for Monocular 3D Object Detection via Spearman Correlation Coefficientcited by 1
  22. 2024DistillGrasp: Integrating Features Correlation with Knowledge Distillation for Depth Completion of Transparent Objectscited by 1
  23. 2025All You Need for Object Detection: From Pixels, Points, and Prompts to Next-Gen Fusion and Multimodal LLMs/VLMs in Autonomous Vehiclescited by 1
  24. 2025LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detectioncited by 1
  25. 2023OriCon3D: Effective 3D Object Detection using Orientation and Confidencecited by 0
  26. 2023Understanding Depth Map Progressively: Adaptive Distance Interval Separation for Monocular 3d Object Detectioncited by 0
  27. 2023Towards Transferable Multi-modal Perception Representation Learning for Autonomy: NeRF-Supervised Masked AutoEncodercited by 0
  28. 2024VaLID: Verification as Late Integration of Detections for LiDAR-Camera Fusioncited by 0
  29. 2025Domain Adaptation-Based Crossmodal Knowledge Distillation for 3D Semantic Segmentationcited by 0
  30. 2025Learning Adaptive Pseudo-Label Selection for Semi-Supervised 3D Object Detectioncited by 0
  31. 2025IMKD: Intensity-Aware Multi-Level Knowledge Distillation for Camera-Radar Fusioncited by 0
  32. 2026LiDAR-Anchored Collaborative Distillation for Robust 2D Representationscited by 0
  33. 2026Selective Transfer Learning of Cross-Modality Distillation for Monocular 3D Object Detectioncited by 0
  34. 2026CRISP: A Spatiotemporal Camera-Radar Backbone for Driving via Forecasting-Based World-Model Pretrainingcited by 0
  35. 2026BucketKD: A Safety-Aware Bucket-Based Knowledge Distillation Framework for End-to-End Motion Planningcited by 0
  36. 2026Efficient Quantization-Aware Distillation with Cross-Modal Alignment for Edge Vision-Language Modelscited by 0