mlsanityData to 7 Oct 2026

BEVPoolv2: A Cutting-edge Implementation of BEVDet Toward Deployment

arXiv 2211.17111 ↗First posted 30 Nov 2022cs.CVcited by 79

Not on the map. Why?

Abstract (arXiv)

We release a new codebase version of the BEVDet, dubbed branch dev2.0. With dev2.0, we propose BEVPoolv2 upgrade the view transformation process from the perspective of engineering optimization, making it free from a huge burden in both calculation and storage aspects. It achieves this by omitting the calculation and preprocessing of the large frustum feature. As a result, it can be processed within 0.82 ms even with a large input resolution of 640x1600, which is 15.1 times the previous fastest implementation. Besides, it is also less cache consumptive when compared with the previous implementation, naturally as it no longer needs to store the large frustum feature. Last but not least, this also makes the deployment to the other backend handy. We offer an example of deployment to the TensorRT backend in branch dev2.0 and show how fast the BEVDet paradigm can be processed on it. Other than BEVPoolv2, we also select and integrate some substantial progress that was proposed in the past year. As an example configuration, BEVDet4D-R50-Depth-CBGS scores 52.3 NDS on the NuScenes validation set and can be processed at a speed of 16.4 FPS with the PyTorch backend. The code has been released to facilitate the study on https://github.com/HuangJunJie2017/BEVDet/tree/dev2.0.

Key facts. Cited by 79 papers in the map (data through 7 Oct 2026). Builds on 12 of its 12 references that are in the map. First posted on arXiv 30 Nov 2022.

Builds on

12 of 12 references.

References · 12

  1. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  2. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  3. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  4. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  5. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  6. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  7. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 334
  8. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  9. 2022BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Drivingcited by 191
  10. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 177
  11. 2022BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereocited by 89
  12. 2022STS: Surround-view Temporal Stereo for Multi-view 3D Detectioncited by 53

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 17; 2024: 33; 2025: 24; 2026: 5.

79 papers.

Sort:

By area:

  1. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 313
  2. 2024SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representationcited by 239
  3. 2023MapTRv2: An End-to-End Framework for Online Vectorized HD Map Constructioncited by 192
  4. 2023Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Drivingcited by 168
  5. 2023SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videoscited by 149
  6. 2023Sparse4D v2: Recurrent Temporal Fusion with Sparse Modelcited by 92
  7. 2024RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detectioncited by 82
  8. 2023Sparse4D v3: Advancing End-to-End 3D Detection and Trackingcited by 69
  9. 2024Leveraging Enhanced Queries of Point Sets for Vectorized Map Constructioncited by 46
  10. 2023Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baselinecited by 40
  11. 2023BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detectioncited by 35
  12. 2024Unleashing HyDRa: Hybrid Fusion, Depth Consistency and Radar for Unified 3D Perceptioncited by 35
38 more
  1. 2024Producing and Leveraging Online Map Uncertainty in Trajectory Predictioncited by 32
  2. 2023SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detectioncited by 30
  3. 2024Enhancing Vectorized Map Perception with Historical Rasterized Mapscited by 29
  4. 2023Detecting As Labeling: Rethinking LiDAR-camera Fusion in 3D Object Detectioncited by 28
  5. 2024MV2DFusion: Leveraging Modality-Specific Object Semantics for Multi-Modal 3D Detectioncited by 23
  6. 2024VEON: Vocabulary-Enhanced Occupancy Predictioncited by 22
  7. 2025Doracamom: Joint 3D Detection and Occupancy Prediction with Multi-view 4D Radars and Cameras for Omnidirectional Perceptioncited by 21
  8. 2024OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networkscited by 17
  9. 2024HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Camerascited by 16
  10. 2024Deep Height Decoupling for Precise Vision-based 3D Occupancy Predictioncited by 16
  11. 2024BEVSpread: Spread Voxel Pooling for Bird's-Eye-View Representation in Vision-based Roadside 3D Object Detectioncited by 15
  12. 2023Surround-View Vision-based 3D Detection for Autonomous Driving: A Surveycited by 14
  13. 2024PrevPredMap: Exploring Temporal Modeling with Previous Predictions for Online Vectorized HD Map Constructioncited by 12
  14. 2024Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagationcited by 12
  15. 2024RCBEVDet++: Toward High-accuracy Radar-Camera Fusion 3D Perception Networkcited by 11
  16. 2024GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detectioncited by 10
  17. 2024DualBEV: Unifying Dual View Transformation with Probabilistic Correspondencescited by 9
  18. 2024Make Your ViT-based Multi-view 3D Detectors Faster via Token Compressioncited by 9
  19. 2025Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Trackingcited by 9
  20. 2024SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perceptioncited by 8
  21. 2024Anchor3DLane++: 3D Lane Detection via Sample-Adaptive Sparse 3D Anchor Regressioncited by 8
  22. 2023Multi-Scale Occ: 4th Place Solution for CVPR 2023 3D Occupancy Prediction Challengecited by 7
  23. 2023A Vision-Centric Approach for Static Map Element Annotationcited by 7
  24. 2024TopoMaskV2: Enhanced Instance-Mask-Based Formulation for the Road Topology Problemcited by 7
  25. 2024Robust 3D Semantic Occupancy Prediction with Calibration-free Spatial Transformationcited by 7
  26. 2024RCTrans: Radar-Camera Transformer via Radar Densifier and Sequential Decoder for 3D Object Detectioncited by 7
  27. 2024LightOcc: Lightweight Spatial Embedding for Efficient Vision-based 3D Occupancy Predictioncited by 6
  28. 2025HENet++: Hybrid Encoding and Multi-task Learning for 3D Perception and End-to-end Autonomous Drivingcited by 6
  29. 2023ClusterFusion: Leveraging Radar Spatial Features for Radar-Camera 3D Object Detection in Autonomous Vehiclescited by 5
  30. 2023QE-BEV: Query Evolution for Bird's Eye View Object Detection in Varied Contextscited by 5
  31. 2024TEOcc: Radar-camera Multi-modal Occupancy Prediction via Temporal Enhancementcited by 5
  32. 2024TopoBDA: Towards Bezier Deformable Attention for Road Topology Understandingcited by 5
  33. 2025Spatial Retrieval Augmented Autonomous Drivingcited by 5
  34. 2023BEVStereo++: Accurate Depth Estimation in Multi-view 3D Object Detection via Dynamic Temporal Stereocited by 4
  35. 2024Multi-Dimensional Pruning: Joint Channel, Layer and Block Pruning with Latency Constraintcited by 4
  36. 2024Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detectioncited by 4
  37. 2024GenMapping: Unleashing the Potential of Inverse Perspective Mapping for Robust Online HD Map Constructioncited by 4
  38. 2025Uni-PrevPredMap: Extending PrevPredMap to a Unified Framework of Prior-Informed Modeling for Online Vectorized HD Map Constructioncited by 4

50 most cited of 79 All 79 (JSON)