mlsanityData to 14 Oct 2026

BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View

arXiv 2112.11790 ↗First posted 22 Dec 2021cs.CVcited by 713

Not on the map. Why?

Cited by 84 in End-to-end autonomous driving, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Autonomous driving perceives its surroundings for decision making, which is one of the most complex scenarios in visual perception. The success of paradigm innovation in solving the 2D object detection task inspires us to seek an elegant, feasible, and scalable paradigm for fundamentally pushing the performance boundary in this area. To this end, we contribute the BEVDet paradigm in this paper. BEVDet performs 3D object detection in Bird-Eye-View (BEV), where most target values are defined and route planning can be handily performed. We merely reuse existing modules to build its framework but substantially develop its performance by constructing an exclusive data augmentation strategy and upgrading the Non-Maximum Suppression strategy. In the experiment, BEVDet offers an excellent trade-off between accuracy and time-efficiency. As a fast version, BEVDet-Tiny scores 31.2% mAP and 39.2% NDS on the nuScenes val set. It is comparable with FCOS3D, but requires just 11% computational budget of 215.3 GFLOPs and runs 9.2 times faster at 15.6 FPS. Another high-precision version dubbed BEVDet-Base scores 39.3% mAP and 47.2% NDS, significantly exceeding all published results. With a comparable inference speed, it surpasses FCOS3D by a large margin of +9.8% mAP and +10.0% NDS. The source code is publicly available for further research at https://github.com/HuangJunJie2017/BEVDet .

Key facts. Cited by 713 papers in the map (data through 14 Oct 2026). Builds on 54 of its 65 references that are in the map. First posted on arXiv 22 Dec 2021.

Builds on

54 of 65 references.

References · 54

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2020End-to-End Object Detection with Transformerscited by 7,414
  7. 2017Mask R-CNNcited by 7,277
  8. 2016Densely Connected Convolutional Networkscited by 6,720
  9. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  10. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  11. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  12. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
38 more
  1. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  2. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  3. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  4. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  5. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  6. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  7. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  8. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  9. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  10. 2019Objects as Pointscited by 1,175
  11. 2020Center-based 3D Object Detection and Trackingcited by 1,144
  12. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
  13. 2020Designing Network Design Spacescited by 960
  14. 2018Path Aggregation Network for Instance Segmentationcited by 798
  15. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  16. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 540
  17. 2019Hybrid Task Cascade for Instance Segmentationcited by 481
  18. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 470
  19. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 447
  20. 2019PointRend: Image Segmentation as Renderingcited by 440
  21. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  22. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 439
  23. 2019Cascade R-CNN: High Quality Object Detection and Instance Segmentationcited by 429
  24. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  25. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 327
  26. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 291
  27. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 249
  28. 2019Disentangling Monocular 3D Object Detectioncited by 217
  29. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 191
  30. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 185
  31. 2020Predicting Semantic Map Representations from Images using Pyramid Occupancy Networkscited by 175
  32. 2019Cross-view Semantic Segmentation for Sensing Surroundingscited by 174
  33. 2020CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detectioncited by 161
  34. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 156
  35. 2020DSGN: Deep Stereo Geometry Network for 3D Object Detectioncited by 101
  36. 2021AutoShape: Real-Time Shape-Aware Monocular 3D Object Detectioncited by 87
  37. 2021Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detectioncited by 84
  38. 2019The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimationcited by 79

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 64; 2023: 158; 2024: 222; 2025: 170; 2026: 99.

713 papers.

Sort:

By area:

  1. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 850
  2. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 572
  3. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 552
  4. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 409
  5. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 352
  6. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 341
  7. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 336
  8. 2024DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Drivingcited by 334
  9. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 332
  10. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 316
  11. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 315
  12. 2022MapTR: Structured Modeling and Learning for Online Vectorized HD Map Constructioncited by 314
38 more
  1. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  2. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 293
  3. 2023NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenariocited by 262
  4. 2023MagicDrive: Street View Generation with Diverse 3D Geometry Controlcited by 252
  5. 2024SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representationcited by 241
  6. 2023OccWorld: Learning a 3D Occupancy World Model for Autonomous Drivingcited by 233
  7. 2024GenAD: Generative End-to-End Autonomous Drivingcited by 225
  8. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 221
  9. 2023Scene as Occupancycited by 209
  10. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  11. 2023MapTRv2: An End-to-End Framework for Online Vectorized HD Map Constructioncited by 193
  12. 2022BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Drivingcited by 191
  13. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 178
  14. 2023Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Drivingcited by 169
  15. 2023Panacea: Panoramic and Controllable Video Generation for Autonomous Drivingcited by 168
  16. 2024Enhancing End-to-End Autonomous Driving with Latent World Modelcited by 166
  17. 2023FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformationcited by 165
  18. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 162
  19. 2024GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Predictioncited by 157
  20. 2023V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perceptioncited by 155
  21. 2022DETRs with Hybrid Matchingcited by 150
  22. 2023SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videoscited by 150
  23. 2025DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Drivingcited by 134
  24. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  25. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  26. 2023RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervisioncited by 128
  27. 2022Vision-Centric BEV Perception: A Surveycited by 126
  28. 2022DeepInteraction: 3D Object Detection via Modality Interactioncited by 125
  29. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  30. 2025Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectivescited by 122
  31. 2022ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queriescited by 117
  32. 2023PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentationcited by 115
  33. 2023FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugincited by 103
  34. 2023Visual Point Cloud Forecasting enables Scalable Autonomous Drivingcited by 99
  35. 2022Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignmentcited by 98
  36. 2023FB-BEV: BEV Representation from Forward-Backward View Transformationscited by 98
  37. 2023COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Predictioncited by 96
  38. 2024SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Predictioncited by 96

50 most cited of 713 All 713 (JSON)