mlsanityData to 14 Oct 2026

Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baseline

arXiv 2301.12511 ↗First posted 29 Jan 2023cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

Recently, perception task based on Bird's-Eye View (BEV) representation has drawn more and more attention, and BEV representation is promising as the foundation for next-generation Autonomous Vehicle (AV) perception. However, most existing BEV solutions either require considerable resources to execute on-vehicle inference or suffer from modest performance. This paper proposes a simple yet effective framework, termed Fast-BEV , which is capable of performing faster BEV perception on the on-vehicle chips. Towards this goal, we first empirically find that the BEV representation can be sufficiently powerful without expensive transformer based transformation nor depth representation. Our Fast-BEV consists of five parts, We novelly propose (1) a lightweight deployment-friendly view transformation which fast transfers 2D image feature to 3D voxel space, (2) an multi-scale image encoder which leverages multi-scale information for better performance, (3) an efficient BEV encoder which is particularly designed to speed up on-vehicle inference. We further introduce (4) a strong data augmentation strategy for both image and BEV space to avoid over-fitting, (5) a multi-frame feature fusion mechanism to leverage the temporal information. Through experiments, on 2080Ti platform, our R50 model can run 52.6 FPS with 47.3% NDS on the nuScenes validation set, exceeding the 41.3 FPS and 47.5% NDS of the BEVDepth-R50 model and 30.2 FPS and 45.7% NDS of the BEVDet4D-R50 model. Our largest model (R101@900x1600) establishes a competitive 53.5% NDS on the nuScenes validation set. We further develop a benchmark with considerable accuracy and efficiency on current popular on-vehicle chips. The code is released at: https://github.com/Sense-GVT/Fast-BEV.

Key facts. Cited by 40 papers in the map (data through 14 Oct 2026). Builds on 37 of its 46 references that are in the map. First posted on arXiv 29 Jan 2023.

Builds on

37 of 46 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  5. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  6. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  7. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  8. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  9. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  10. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  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
25 more
  1. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  2. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 850
  3. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 713
  4. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  5. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 572
  6. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 552
  7. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 447
  8. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 352
  9. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  10. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 341
  11. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 327
  12. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  13. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 252
  14. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 249
  15. 2020Atlas: End-to-End 3D Scene Reconstruction from Posed Imagescited by 206
  16. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 202
  17. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 191
  18. 2021ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detectioncited by 157
  19. 2022M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representationcited by 156
  20. 2022PolarFormer: Multi-camera 3D Object Detection with Polar Transformercited by 147
  21. 2021Translating Images into Mapscited by 115
  22. 2022BEVPoolv2: A Cutting-edge Implementation of BEVDet Toward Deploymentcited by 79
  23. 2022Learning Ego 3D Representation as Ray Tracingcited by 43
  24. 2022Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detectioncited by 35
  25. 2022MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perceptioncited by 29

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 16; 2025: 10; 2026: 7.

40 papers.

Sort:

By area:

  1. 2023FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugincited by 103
  2. 2023DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Drivingcited by 73
  3. 2023UniWorld: Autonomous Driving Pre-training via World Modelscited by 33
  4. 2023BEVHeight++: Toward Robust Visual Centric 3D Object Detectioncited by 30
  5. 2024Is Your HD Map Constructor Reliable under Sensor Corruptions?cited by 28
  6. 2023Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Reviewcited by 25
  7. 2024Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunitiescited by 24
  8. 2025Doracamom: Joint 3D Detection and Occupancy Prediction with Multi-view 4D Radars and Cameras for Omnidirectional Perceptioncited by 22
  9. 2023HeightFormer: Explicit Height Modeling without Extra Data for Camera-only 3D Object Detection in Bird's Eye Viewcited by 19
  10. 2024OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networkscited by 17
  11. 2025AutoOcc: Automatic Open-Ended Semantic Occupancy Annotation via Vision-Language Guided Gaussian Splattingcited by 14
  12. 2024SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objectscited by 12
28 more
  1. 2024Make Your ViT-based Multi-view 3D Detectors Faster via Token Compressioncited by 9
  2. 2024SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perceptioncited by 8
  3. 2025Semantic Causality-Aware Vision-Based 3D Occupancy Predictioncited by 8
  4. 2023NVAutoNet: Fast and Accurate 360circ 3D Visual Perception For Self Drivingcited by 6
  5. 2025CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detectorcited by 6
  6. 2024WidthFormer: Toward Efficient Transformer-based BEV View Transformationcited by 5
  7. 2024TempBEV: Improving Learned BEV Encoders with Combined Image and BEV Space Temporal Aggregationcited by 5
  8. 2024RopeBEV: A Multi-Camera Roadside Perception Network in Bird's-Eye-Viewcited by 5
  9. 2024TopoBDA: Towards Bezier Deformable Attention for Road Topology Understandingcited by 5
  10. 2024LiDAR-based End-to-end Temporal Perception for Vehicle-Infrastructure Cooperationcited by 4
  11. 2025TransParking: A Dual-Decoder Transformer Framework with Soft Localization for End-to-End Automatic Parkingcited by 4
  12. 2026Towards Intrinsic-Aware Monocular 3D Object Detectioncited by 4
  13. 2024HV-BEV: Decoupling Horizontal and Vertical Feature Sampling for Multi-View 3D Object Detectioncited by 3
  14. 2025HeightFormer: Learning Height Prediction in Voxel Features for Roadside Vision Centric 3D Object Detection via Transformercited by 3
  15. 2024Hierarchical and Decoupled BEV Perception Learning Framework for Autonomous Drivingcited by 2
  16. 2024Vision-Driven 2D Supervised Fine-Tuning Framework for Bird's Eye View Perceptioncited by 2
  17. 2024EVT: Efficient View Transformation for Multi-Modal 3D Object Detectioncited by 2
  18. 2025Stereo-based 3D Anomaly Object Detection for Autonomous Driving: A New Dataset and Baselinecited by 2
  19. 2025Fast-BEV++: Fast by Algorithm, Deployable by Designcited by 2
  20. 2025SimBEV: A Synthetic Multi-Task Multi-Sensor Driving Data Generation Tool and Datasetcited by 1
  21. 2026TopoMaskV3: 3D Mask Head with Dense Offset and Height Predictions for Road Topology Understandingcited by 1
  22. 2024KAN-RCBEVDepth: A multi-modal fusion algorithm in object detection for autonomous drivingcited by 0
  23. 2025StereoMV2D: A Sparse Temporal Stereo-Enhanced Framework for Robust Multi-View 3D Object Detectioncited by 0
  24. 2026OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RLcited by 0
  25. 2026Understanding Cross-Rig Generalization in Automotive Perception: a Multi-Rig Benchmark and Rig Variation Metricscited by 0
  26. 2026FlashBEV: Fast and Memory-Efficient Exact BEV Transformation with IO-Awarenesscited by 0
  27. 2026Infrastructure-based Monocular 3D Vehicle Localization Framework with Experimental Validationcited by 0
  28. 2026Bi-Level Routing and Sparse Spatial Attention based Multi-View BEV 3D Object Detection for Autonomous Drivingcited by 0