mlsanityData to 7 Oct 2026

FB-BEV: BEV Representation from Forward-Backward View Transformations

arXiv 2308.02236 ↗First posted 4 Aug 2023cs.CVcited by 98

Not on the map. Why?

Abstract (arXiv)

View Transformation Module (VTM), where transformations happen between multi-view image features and Bird-Eye-View (BEV) representation, is a crucial step in camera-based BEV perception systems. Currently, the two most prominent VTM paradigms are forward projection and backward projection. Forward projection, represented by Lift-Splat-Shoot, leads to sparsely projected BEV features without post-processing. Backward projection, with BEVFormer being an example, tends to generate false-positive BEV features from incorrect projections due to the lack of utilization on depth. To address the above limitations, we propose a novel forward-backward view transformation module. Our approach compensates for the deficiencies in both existing methods, allowing them to enhance each other to obtain higher quality BEV representations mutually. We instantiate the proposed module with FB-BEV, which achieves a new state-of-the-art result of 62.4% NDS on the nuScenes test set. Code and models are available at https://github.com/NVlabs/FB-BEV.

Key facts. Cited by 98 papers in the map (data through 7 Oct 2026). Builds on 44 of its 50 references that are in the map. First posted on arXiv 4 Aug 2023.

Builds on

44 of 50 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2022A ConvNet for the 2020scited by 3,545
  5. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  6. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  7. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  8. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  9. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  10. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  11. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  12. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
32 more
  1. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  2. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  3. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  4. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  5. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 351
  6. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  7. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  8. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 334
  9. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 326
  10. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 313
  11. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  12. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  13. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  14. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 201
  15. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 177
  16. 2019An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detectioncited by 163
  17. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 161
  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 155
  20. 2022PolarFormer: Multi-camera 3D Object Detection with Polar Transformercited by 147
  21. 2022PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmarkcited by 140
  22. 2022BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigscited by 123
  23. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  24. 2021Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformerscited by 109
  25. 2023Sparse4D v2: Recurrent Temporal Fusion with Sparse Modelcited by 92
  26. 2022BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereocited by 89
  27. 2019What You See is What You Get: Exploiting Visibility for 3D Object Detectioncited by 69
  28. 2022Polar Parametrization for Vision-based Surround-View 3D Detectioncited by 53
  29. 2022STS: Surround-view Temporal Stereo for Multi-view 3D Detectioncited by 53
  30. 2022MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perceptioncited by 29
  31. 2022DETR4D: Direct Multi-View 3D Object Detection with Sparse Attentioncited by 21
  32. 2022Multi-Camera Calibration Free BEV Representation for 3D Object Detectioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 9; 2024: 41; 2025: 34; 2026: 14.

98 papers.

Sort:

By area:

  1. 2023Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?cited by 242
  2. 2023Visual Point Cloud Forecasting enables Scalable Autonomous Drivingcited by 97
  3. 2023COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Predictioncited by 94
  4. 2024FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird's-Eye View and Perspective Viewcited by 51
  5. 2023OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queriescited by 48
  6. 2024Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillationcited by 43
  7. 2023Memory-and-Anticipation Transformer for Online Action Understandingcited by 39
  8. 2023OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environmentscited by 39
  9. 2024ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformerscited by 36
  10. 2023BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detectioncited by 35
  11. 2024Unleashing HyDRa: Hybrid Fusion, Depth Consistency and Radar for Unified 3D Perceptioncited by 35
  12. 2024Vision-based 3D occupancy prediction in autonomous driving: a review and outlookcited by 29
38 more
  1. 2024Enhancing Vectorized Map Perception with Historical Rasterized Mapscited by 29
  2. 2024PreSight: Enhancing Autonomous Vehicle Perception with City-Scale NeRF Priorscited by 21
  3. 2024Navigation Instruction Generation with BEV Perception and Large Language Modelscited by 20
  4. 2025Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splattingcited by 20
  5. 2025STCOcc: Sparse Spatial-Temporal Cascade Renovation for 3D Occupancy and Scene Flow Predictioncited by 20
  6. 2025DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Drivingcited by 20
  7. 2024ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictionscited by 19
  8. 2024RaCFormer: Towards High-Quality 3D Object Detection via Query-based Radar-Camera Fusioncited by 19
  9. 2024OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networkscited by 17
  10. 2024HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Camerascited by 16
  11. 2025OccVLA: Vision-Language-Action Model with Implicit 3D Occupancy Supervisioncited by 16
  12. 2024AD-H: Language-guided Autonomous Driving with Hierarchical Agentscited by 15
  13. 2024DAOcc: 3D Object Detection Assisted Multi-Sensor Fusion for 3D Occupancy Predictioncited by 15
  14. 2024InverseMatrixVT3D: An Efficient Projection Matrix-Based Approach for 3D Occupancy Predictioncited by 14
  15. 2024GAFusion: Adaptive Fusing LiDAR and Camera with Multiple Guidance for 3D Object Detectioncited by 14
  16. 2023Regulating Intermediate 3D Features for Vision-Centric Autonomous Drivingcited by 12
  17. 2024SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objectscited by 12
  18. 2024CountFormer: Multi-View Crowd Counting Transformercited by 12
  19. 2024SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Fieldcited by 10
  20. 2024GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detectioncited by 10
  21. 2024DualBEV: Unifying Dual View Transformation with Probabilistic Correspondencescited by 9
  22. 2024LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object Detectioncited by 9
  23. 2024RayFormer: Improving Query-Based Multi-Camera 3D Object Detection via Ray-Centric Strategiescited by 9
  24. 2024FlatFusion: Delving into Details of Sparse Transformer-based Camera-LiDAR Fusion for Autonomous Drivingcited by 9
  25. 2024Make Your ViT-based Multi-view 3D Detectors Faster via Token Compressioncited by 9
  26. 2024SpaRC: Sparse Radar-Camera Fusion for 3D Object Detectioncited by 8
  27. 2025Occupancy Learning with Spatiotemporal Memorycited by 8
  28. 2025Semantic Causality-Aware Vision-Based 3D Occupancy Predictioncited by 8
  29. 2024Robust 3D Semantic Occupancy Prediction with Calibration-free Spatial Transformationcited by 7
  30. 2025RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embeddingcited by 7
  31. 2024FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object Detectioncited by 6
  32. 2025AugMapNet: Improving Spatial Latent Structure via BEV Grid Augmentation for Enhanced Vectorized Online HD Map Constructioncited by 6
  33. 2025Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimationcited by 6
  34. 2025HENet++: Hybrid Encoding and Multi-task Learning for 3D Perception and End-to-end Autonomous Drivingcited by 6
  35. 2024RoadRunner M&M -- Learning Multi-range Multi-resolution Traversability Maps for Autonomous Off-road Navigationcited by 5
  36. 2024Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detectioncited by 4
  37. 2024Task Weighting through Gradient Projection for Multitask Learningcited by 4
  38. 2024MambaBEV: An EV-based 3D detection model with Mamba2cited by 4

50 most cited of 98 All 98 (JSON)