mlsanityData to 14 Oct 2026

DualBEV: Unifying Dual View Transformation with Probabilistic Correspondences

arXiv 2403.05402 ↗First posted 8 Mar 2024cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Camera-based Bird's-Eye-View (BEV) perception often struggles between adopting 3D-to-2D or 2D-to-3D view transformation (VT). The 3D-to-2D VT typically employs resource-intensive Transformer to establish robust correspondences between 3D and 2D features, while the 2D-to-3D VT utilizes the Lift-Splat-Shoot (LSS) pipeline for real-time application, potentially missing distant information. To address these limitations, we propose DualBEV, a unified framework that utilizes a shared feature transformation incorporating three probabilistic measurements for both strategies. By considering dual-view correspondences in one stage, DualBEV effectively bridges the gap between these strategies, harnessing their individual strengths. Our method achieves state-of-the-art performance without Transformer, delivering comparable efficiency to the LSS approach, with 55.2% mAP and 63.4% NDS on the nuScenes test set. Code is available at urlhttps://github.com/PeidongLi/DualBEV

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 37 of its 41 references that are in the map. First posted on arXiv 8 Mar 2024.

Builds on

37 of 41 references.

References · 37

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  5. 2022A ConvNet for the 2020scited by 3,579
  6. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  7. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  8. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  9. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
  10. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 713
  11. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  12. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 572
25 more
  1. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 552
  2. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 352
  3. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  4. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 341
  5. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  6. 2022Vision Transformer with Deformable Attentioncited by 295
  7. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 202
  8. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  9. 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 201
  10. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 178
  11. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 162
  12. 2022M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representationcited by 156
  13. 2023SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videoscited by 150
  14. 2022PolarFormer: Multi-camera 3D Object Detection with Polar Transformercited by 147
  15. 2022Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?cited by 128
  16. 2020Attentional Feature Fusioncited by 115
  17. 2023FB-BEV: BEV Representation from Forward-Backward View Transformationscited by 98
  18. 2022BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereocited by 90
  19. 2022BEVPoolv2: A Cutting-edge Implementation of BEVDet Toward Deploymentcited by 79
  20. 2023CAPE: Camera View Position Embedding for Multi-View 3D Object Detectioncited by 40
  21. 2022TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learningcited by 37
  22. 2023SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detectioncited by 30
  23. 2022MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perceptioncited by 29
  24. 2022BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networkscited by 20
  25. 2023HeightFormer: Explicit Height Modeling without Extra Data for Camera-only 3D Object Detection in Bird's Eye Viewcited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 4.

9 papers.

  1. 2024Navigation-Guided Sparse Scene Representation for End-to-End Autonomous Drivingcited by 46
  2. 2025TransParking: A Dual-Decoder Transformer Framework with Soft Localization for End-to-End Automatic Parkingcited by 4
  3. 2025SA-Occ: Satellite-Assisted 3D Occupancy Prediction in Real Worldcited by 3
  4. 2025RESAR-BEV: An Explainable Progressive Residual Autoregressive Approach for Camera-Radar Fusion in BEV Segmentationcited by 2
  5. 2025MAESTRO: Task-Relevant Optimization via Adaptive Feature Enhancement and Suppression for Multi-task 3D Perceptioncited by 0
  6. 2026SDCM: Simulated Densifying and Compensatory Modeling Fusion for Radar-Vision 3-D Object Detection in Internet of Vehiclescited by 0
  7. 2026Faster Training, Fewer Labels: Self-Supervised Pretraining for Fine-Grained BEV Segmentationcited by 0
  8. 2026RayD3D: Distilling Depth Knowledge Along the Ray for Robust Multi-View 3D Object Detectioncited by 0
  9. 2026FlashBEV: Fast and Memory-Efficient Exact BEV Transformation with IO-Awarenesscited by 0