mlsanityData to 7 Oct 2026

Vision-Centric BEV Perception: A Survey

arXiv 2208.02797 ↗First posted 4 Aug 2022cs.CVcited by 126

Not on the map. Why?

Abstract (arXiv)

In recent years, vision-centric Bird's Eye View (BEV) perception has garnered significant interest from both industry and academia due to its inherent advantages, such as providing an intuitive representation of the world and being conducive to data fusion. The rapid advancements in deep learning have led to the proposal of numerous methods for addressing vision-centric BEV perception challenges. However, there has been no recent survey encompassing this novel and burgeoning research field. To catalyze future research, this paper presents a comprehensive survey of the latest developments in vision-centric BEV perception and its extensions. It compiles and organizes up-to-date knowledge, offering a systematic review and summary of prevalent algorithms. Additionally, the paper provides in-depth analyses and comparative results on various BEV perception tasks, facilitating the evaluation of future works and sparking new research directions. Furthermore, the paper discusses and shares valuable empirical implementation details to aid in the advancement of related algorithms.

Key facts. Cited by 126 papers in the map (data through 7 Oct 2026). Builds on 119 of its 180 references that are in the map. First posted on arXiv 4 Aug 2022.

Builds on

119 of 180 references.

References · 119

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020End-to-End Object Detection with Transformerscited by 7,384
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  7. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  8. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  9. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  10. 2020Reformer: The Efficient Transformercited by 1,658
  11. 2017Deformable Convolutional Networkscited by 1,481
  12. 2020Linformer: Self-Attention with Linear Complexitycited by 1,462
38 more
  1. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  2. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  3. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  4. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  5. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 852
  6. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  7. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  8. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  9. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  10. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  11. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  12. 2017Generative Adversarial Networks: An Overviewcited by 588
  13. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  14. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  15. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  16. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  17. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  18. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  19. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  20. 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
  21. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  22. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
  23. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 351
  24. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  25. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  26. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 326
  27. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  28. 2021HDMapNet: An Online HD Map Construction and Evaluation Frameworkcited by 280
  29. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  30. 2020Deep Continuous Fusion for Multi-Sensor 3D Object Detectioncited by 263
  31. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
  32. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 251
  33. 2020Sparse Sinkhorn Attentioncited by 250
  34. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  35. 2021FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Camerascited by 239
  36. 2022CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformerscited by 227
  37. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  38. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 201

50 most cited of 119 All 119 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 42; 2024: 37; 2025: 26; 2026: 15.

126 papers.

Sort:

By area:

  1. 2022MapTR: Structured Modeling and Learning for Online Vectorized HD Map Constructioncited by 311
  2. 2023MapTRv2: An End-to-End Framework for Online Vectorized HD Map Constructioncited by 192
  3. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  4. 2024Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Modelscited by 75
  5. 2023SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Drivingcited by 72
  6. 2023Bird's-Eye-View Scene Graph for Vision-Language Navigationcited by 71
  7. 2024MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mappingcited by 67
  8. 2023LXL: LiDAR Excluded Lean 3D Object Detection with 4D Imaging Radar and Camera Fusioncited by 57
  9. 2022Uncertainty-aware Vision-based Metric Cross-view Geolocalizationcited by 54
  10. 2023Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Constructioncited by 50
  11. 2024GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splattingcited by 50
  12. 2023RoboBEV: Towards Robust Bird's Eye View Perception under Corruptionscited by 42
38 more
  1. 2023InstaGraM: Instance-level Graph Modeling for Vectorized HD Map Learningcited by 40
  2. 2022SuperFusion: Multilevel LiDAR-Camera Fusion for Long-Range HD Map Generationcited by 39
  3. 2024Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Drivingcited by 39
  4. 2023Among Us: Adversarially Robust Collaborative Perception by Consensuscited by 37
  5. 2024A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspectivecited by 37
  6. 2023UniWorld: Autonomous Driving Pre-training via World Modelscited by 32
  7. 2023BEVFusion4D: Learning LiDAR-Camera Fusion Under Bird's-Eye-View via Cross-Modality Guidance and Temporal Aggregationcited by 31
  8. 2023Data-driven Traffic Simulation: A Comprehensive Reviewcited by 29
  9. 2024Vision-based 3D occupancy prediction in autonomous driving: a review and outlookcited by 29
  10. 2024Is Your HD Map Constructor Reliable under Sensor Corruptions?cited by 28
  11. 2023Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-Viewcited by 27
  12. 2025CoSDH: Communication-Efficient Collaborative Perception via Supply-Demand Awareness and Intermediate-Late Hybridizationcited by 27
  13. 2023Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Reviewcited by 25
  14. 2022Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmarkcited by 24
  15. 2024Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunitiescited by 24
  16. 2024The RoboDrive Challenge: Drive Anytime Anywhere in Any Conditioncited by 23
  17. 2024GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervisioncited by 21
  18. 2024Navigation Instruction Generation with BEV Perception and Large Language Modelscited by 20
  19. 2022Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detectioncited by 19
  20. 2025LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenescited by 19
  21. 2023On the Adversarial Robustness of Camera-based 3D Object Detectioncited by 15
  22. 2023Calibration-free BEV Representation for Infrastructure Perceptioncited by 15
  23. 2023UniScene: Multi-Camera Unified Pre-training via 3D Scene Reconstruction for Autonomous Drivingcited by 15
  24. 2024BEVSpread: Spread Voxel Pooling for Bird's-Eye-View Representation in Vision-based Roadside 3D Object Detectioncited by 15
  25. 2023Surround-View Vision-based 3D Detection for Autonomous Driving: A Surveycited by 14
  26. 2023FedBEVT: Federated Learning Bird's Eye View Perception Transformer in Road Traffic Systemscited by 14
  27. 2024GAFusion: Adaptive Fusing LiDAR and Camera with Multiple Guidance for 3D Object Detectioncited by 14
  28. 2025Rethinking Driving World Model as Synthetic Data Generator for Perception Taskscited by 14
  29. 2023Bi-Mapper: Holistic BEV Semantic Mapping for Autonomous Drivingcited by 13
  30. 2023AmodalSynthDrive: A Synthetic Amodal Perception Dataset for Autonomous Drivingcited by 13
  31. 2023F2BEV: Bird's Eye View Generation from Surround-View Fisheye Camera Images for Automated Drivingcited by 12
  32. 2023VIMI: Vehicle-Infrastructure Multi-view Intermediate Fusion for Camera-based 3D Object Detectioncited by 12
  33. 2024SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objectscited by 12
  34. 2025SafeMap: Robust HD Map Construction from Incomplete Observationscited by 12
  35. 2023Adv3D: Generating 3D Adversarial Examples for 3D Object Detection in Driving Scenarios with NeRFcited by 10
  36. 2024BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Drivingcited by 10
  37. 2023Navya3DSeg -- Navya 3D Semantic Segmentation Dataset & split generation for autonomous vehiclescited by 9
  38. 2023VMA: Divide-and-Conquer Vectorized Map Annotation System for Large-Scale Driving Scenecited by 9

50 most cited of 126 All 126 (JSON)