mlsanityData to 7 Oct 2026

BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection

arXiv 2206.10092 ↗First posted 21 Jun 2022cs.CVcited by 568

Not on the map. Why?

Cited by 53 in End-to-end autonomous driving, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In this research, we propose a new 3D object detector with a trustworthy depth estimation, dubbed BEVDepth, for camera-based Bird's-Eye-View (BEV) 3D object detection. Our work is based on a key observation -- depth estimation in recent approaches is surprisingly inadequate given the fact that depth is essential to camera 3D detection. Our BEVDepth resolves this by leveraging explicit depth supervision. A camera-awareness depth estimation module is also introduced to facilitate the depth predicting capability. Besides, we design a novel Depth Refinement Module to counter the side effects carried by imprecise feature unprojection. Aided by customized Efficient Voxel Pooling and multi-frame mechanism, BEVDepth achieves the new state-of-the-art 60.9% NDS on the challenging nuScenes test set while maintaining high efficiency. For the first time, the NDS score of a camera model reaches 60%.

Key facts. Cited by 568 papers in the map (data through 7 Oct 2026). Builds on 46 of its 53 references that are in the map. First posted on arXiv 21 Jun 2022.

Builds on

46 of 53 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020End-to-End Object Detection with Transformerscited by 7,384
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2022A ConvNet for the 2020scited by 3,545
  6. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  7. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  8. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  9. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  10. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  11. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  12. 2019Objects as Pointscited by 1,172
34 more
  1. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  2. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  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. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  6. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  7. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  8. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  9. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  10. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  11. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  12. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  13. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  14. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  15. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  16. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  17. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 414
  18. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 351
  19. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  20. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  21. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 326
  22. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 252
  23. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 251
  24. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  25. 2020PatchmatchNet: Learned Multi-View Patchmatch Stereocited by 204
  26. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 201
  27. 2020Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformerscited by 190
  28. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 190
  29. 2019Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Drivingcited by 188
  30. 2019Learning Depth-Guided Convolutions for Monocular 3D Object Detectioncited by 169
  31. 2021ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detectioncited by 157
  32. 2022DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimationcited by 116
  33. 2020End-to-End Pseudo-LiDAR for Image-Based 3D Object Detectioncited by 80
  34. 2021Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometrycited by 46

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 33; 2023: 135; 2024: 184; 2025: 134; 2026: 82.

568 papers.

Sort:

By area:

  1. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  2. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  3. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 325
  4. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 313
  5. 2022MapTR: Structured Modeling and Learning for Online Vectorized HD Map Constructioncited by 311
  6. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  7. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  8. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 287
  9. 2024VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planningcited by 287
  10. 2023NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenariocited by 258
  11. 2023Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?cited by 242
  12. 2024SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representationcited by 239
38 more
  1. 2023OccWorld: Learning a 3D Occupancy World Model for Autonomous Drivingcited by 230
  2. 2024GenAD: Generative End-to-End Autonomous Drivingcited by 225
  3. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 218
  4. 2023Scene as Occupancycited by 208
  5. 2023MapTRv2: An End-to-End Framework for Online Vectorized HD Map Constructioncited by 192
  6. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 177
  7. 2023Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Drivingcited by 168
  8. 2023Panacea: Panoramic and Controllable Video Generation for Autonomous Drivingcited by 165
  9. 2023FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformationcited by 162
  10. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 161
  11. 2024GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Predictioncited by 155
  12. 2023SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videoscited by 149
  13. 2023DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Drivingcited by 142
  14. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  15. 2024DreamBench++: A Human-Aligned Benchmark for Personalized Image Generationcited by 131
  16. 2022Vision-Centric BEV Perception: A Surveycited by 126
  17. 2023RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervisioncited by 126
  18. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  19. 2023PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentationcited by 114
  20. 2023FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugincited by 101
  21. 2023FB-BEV: BEV Representation from Forward-Backward View Transformationscited by 98
  22. 2023Visual Point Cloud Forecasting enables Scalable Autonomous Drivingcited by 97
  23. 2023COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Predictioncited by 94
  24. 2024SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Predictioncited by 94
  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. 2023OccDepth: A Depth-Aware Method for 3D Semantic Scene Completioncited by 85
  28. 2023SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detectioncited by 83
  29. 2024GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Predictioncited by 83
  30. 2024RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detectioncited by 82
  31. 2023CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perceptioncited by 81
  32. 2022BEVPoolv2: A Cutting-edge Implementation of BEVDet Toward Deploymentcited by 79
  33. 2023BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detectioncited by 74
  34. 2023UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representationcited by 74
  35. 2023UniPAD: A Universal Pre-training Paradigm for Autonomous Drivingcited by 73
  36. 2023Bird's-Eye-View Scene Graph for Vision-Language Navigationcited by 71
  37. 2023Far3D: Expanding the Horizon for Surround-view 3D Object Detectioncited by 70
  38. 2023Sparse4D v3: Advancing End-to-End 3D Detection and Trackingcited by 69

50 most cited of 568 All 568 (JSON)