mlsanityData to 7 Oct 2026

BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision

arXiv 2211.10439 ↗First posted 18 Nov 2022cs.CVcited by 302

Not on the map. Why?

Cited by 38 in End-to-end autonomous driving, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present a novel bird's-eye-view (BEV) detector with perspective supervision, which converges faster and better suits modern image backbones. Existing state-of-the-art BEV detectors are often tied to certain depth pre-trained backbones like VoVNet, hindering the synergy between booming image backbones and BEV detectors. To address this limitation, we prioritize easing the optimization of BEV detectors by introducing perspective space supervision. To this end, we propose a two-stage BEV detector, where proposals from the perspective head are fed into the bird's-eye-view head for final predictions. To evaluate the effectiveness of our model, we conduct extensive ablation studies focusing on the form of supervision and the generality of the proposed detector. The proposed method is verified with a wide spectrum of traditional and modern image backbones and achieves new SoTA results on the large-scale nuScenes dataset. The code shall be released soon.

Key facts. Cited by 302 papers in the map (data through 7 Oct 2026). Builds on 40 of its 46 references that are in the map. First posted on arXiv 18 Nov 2022.

Builds on

40 of 46 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  6. 2022A ConvNet for the 2020scited by 3,545
  7. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  8. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  9. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  10. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  11. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  12. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
28 more
  1. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  2. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  3. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  4. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  5. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  6. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 479
  7. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  8. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  9. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  10. 2017Deep Layer Aggregationcited by 436
  11. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 351
  12. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  13. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  14. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  15. 2021FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Camerascited by 239
  16. 2019Disentangling Monocular 3D Object Detectioncited by 215
  17. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 201
  18. 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 200
  19. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 184
  20. 2019Cross-view Semantic Segmentation for Sensing Surroundingscited by 173
  21. 2022PolarFormer: Multi-camera 3D Object Detection with Polar Transformercited by 147
  22. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  23. 2022Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?cited by 128
  24. 2022BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereocited by 89
  25. 2021Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detectioncited by 66
  26. 2022STS: Surround-view Temporal Stereo for Multi-view 3D Detectioncited by 53
  27. 2022MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbonescited by 29
  28. 2022A Simple Baseline for Multi-Camera 3D Object Detectioncited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 49; 2024: 124; 2025: 85; 2026: 44.

302 papers.

Sort:

By area:

  1. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 313
  2. 2024VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planningcited by 287
  3. 2023Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?cited by 242
  4. 2024SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representationcited by 239
  5. 2023DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Drivingcited by 233
  6. 2024GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Predictioncited by 155
  7. 2023SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videoscited by 149
  8. 2023StreamMapNet: Streaming Mapping Network for Vectorized Online HD Map Constructioncited by 143
  9. 2025DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Drivingcited by 125
  10. 2023PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentationcited by 114
  11. 2023FB-BEV: BEV Representation from Forward-Backward View Transformationscited by 98
  12. 2023Visual Point Cloud Forecasting enables Scalable Autonomous Drivingcited by 97
38 more
  1. 2023COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Predictioncited by 94
  2. 2023Sparse4D v2: Recurrent Temporal Fusion with Sparse Modelcited by 92
  3. 2025World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Modelcited by 91
  4. 2024OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Drivingcited by 76
  5. 2023UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representationcited by 74
  6. 2023UniPAD: A Universal Pre-training Paradigm for Autonomous Drivingcited by 73
  7. 2023Far3D: Expanding the Horizon for Surround-view 3D Object Detectioncited by 70
  8. 2023Sparse4D v3: Advancing End-to-End 3D Detection and Trackingcited by 69
  9. 2024MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mappingcited by 67
  10. 2023Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perceptioncited by 65
  11. 2025HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generationcited by 56
  12. 2023Online Map Vectorization for Autonomous Driving: A Rasterization Perspectivecited by 54
  13. 2025DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Drivingcited by 52
  14. 2024FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird's-Eye View and Perspective Viewcited by 51
  15. 2024Context and Geometry Aware Voxel Transformer for Semantic Scene Completioncited by 50
  16. 2023Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Predictioncited by 49
  17. 2024Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applicationscited by 49
  18. 2023OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queriescited by 48
  19. 2024SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Drivingcited by 46
  20. 2024RenderWorld: World Model with Self-Supervised 3D Labelcited by 44
  21. 2024Stream Query Denoising for Vectorized HD Map Constructioncited by 43
  22. 2025DriveLaW:Unifying Planning and Video Generation in a Latent Driving Worldcited by 43
  23. 2024Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detectioncited by 36
  24. 2023BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detectioncited by 35
  25. 2024Unleashing HyDRa: Hybrid Fusion, Depth Consistency and Radar for Unified 3D Perceptioncited by 35
  26. 2024MS-DETR: Efficient DETR Training with Mixed Supervisioncited by 34
  27. 2023PPAD: Iterative Interactions of Prediction and Planning for End-to-end Autonomous Drivingcited by 33
  28. 2024GraphBEV: Towards Robust BEV Feature Alignment for Multi-Modal 3D Object Detectioncited by 33
  29. 2024ADA-Track++: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Associationcited by 33
  30. 2023UniWorld: Autonomous Driving Pre-training via World Modelscited by 32
  31. 2024OccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Predictioncited by 32
  32. 2023Fully Sparse Fusion for 3D Object Detectioncited by 29
  33. 2024SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decompositioncited by 29
  34. 2024Monocular Occupancy Prediction for Scalable Indoor Scenescited by 29
  35. 2024Is Your HD Map Constructor Reliable under Sensor Corruptions?cited by 28
  36. 2024MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillationcited by 26
  37. 2023Echoes Beyond Points: Unleashing the Power of Raw Radar Data in Multi-modality Fusioncited by 25
  38. 2024SparseLIF: High-Performance Sparse LiDAR-Camera Fusion for 3D Object Detectioncited by 25

50 most cited of 302 All 302 (JSON)