mlsanityData to 7 Oct 2026

BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection

arXiv 2312.01696 ↗First posted 4 Dec 2023cs.CVcited by 35

Not on the map. Why?

Abstract (arXiv)

Recently, the rise of query-based Transformer decoders is reshaping camera-based 3D object detection. These query-based decoders are surpassing the traditional dense BEV (Bird's Eye View)-based methods. However, we argue that dense BEV frameworks remain important due to their outstanding abilities in depth estimation and object localization, depicting 3D scenes accurately and comprehensively. This paper aims to address the drawbacks of the existing dense BEV-based 3D object detectors by introducing our proposed enhanced components, including a CRF-modulated depth estimation module enforcing object-level consistencies, a long-term temporal aggregation module with extended receptive fields, and a two-stage object decoder combining perspective techniques with CRF-modulated depth embedding. These enhancements lead to a "modernized" dense BEV framework dubbed BEVNeXt. On the nuScenes benchmark, BEVNeXt outperforms both BEV-based and query-based frameworks under various settings, achieving a state-of-the-art result of 64.2 NDS on the nuScenes test set. Code will be available at urlhttps://github.com/woxihuanjiangguo/BEVNeXt.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 63 of its 70 references that are in the map. First posted on arXiv 4 Dec 2023.

Builds on

63 of 70 references.

References · 63

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  9. 2022A ConvNet for the 2020scited by 3,545
  10. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  11. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  12. 2020Center-based 3D Object Detection and Trackingcited by 1,143
38 more
  1. 2022Planning-oriented Autonomous Drivingcited by 1,068
  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. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  6. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  7. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  8. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  9. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 479
  10. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 468
  11. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  12. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  13. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 351
  14. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  15. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  16. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 325
  17. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 313
  18. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  19. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  20. 2021FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Camerascited by 239
  21. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  22. 2015Conditional Random Fields as Recurrent Neural Networkscited by 213
  23. 2023Scene as Occupancycited by 208
  24. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 177
  25. 2021Scene Transformer: A unified architecture for predicting multiple agent trajectoriescited by 165
  26. 2019An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detectioncited by 163
  27. 2023FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformationcited by 162
  28. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 161
  29. 2023SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videoscited by 149
  30. 2022DeepInteraction: 3D Object Detection via Modality Interactioncited by 125
  31. 2023Motion Planning for Autonomous Driving: The State of the Art and Future Perspectivescited by 112
  32. 2014Deep Convolutional Neural Fields for Depth Estimation from a Single Imagecited by 106
  33. 2022CenterFormer: Center-based Transformer for 3D Object Detectioncited by 99
  34. 2023FB-BEV: BEV Representation from Forward-Backward View Transformationscited by 98
  35. 2022SWFormer: Sparse Window Transformer for 3D Object Detection in Point Cloudscited by 92
  36. 2023Sparse4D v2: Recurrent Temporal Fusion with Sparse Modelcited by 92
  37. 2016Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networkscited by 91
  38. 2022BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereocited by 89

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 14; 2026: 12.

35 papers.

Sort:

By area:

  1. 2024UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehiclescited by 16
  2. 2025Perspective-Invariant 3D Object Detectioncited by 16
  3. 2024AD-H: Language-guided Autonomous Driving with Hierarchical Agentscited by 15
  4. 2024SimPB: A Single Model for 2D and 3D Object Detection from Multiple Camerascited by 9
  5. 2024Make Your ViT-based Multi-view 3D Detectors Faster via Token Compressioncited by 9
  6. 2025Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Trackingcited by 9
  7. 2026DriveMamba: Task-Centric Scalable State Space Model for Efficient End-to-End Autonomous Drivingcited by 9
  8. 2024SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perceptioncited by 8
  9. 2024SpaRC: Sparse Radar-Camera Fusion for 3D Object Detectioncited by 8
  10. 2025Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labelscited by 7
  11. 2024LightOcc: Lightweight Spatial Embedding for Efficient Vision-based 3D Occupancy Predictioncited by 6
  12. 2024Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detectioncited by 4
23 more
  1. 2025CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detectorcited by 4
  2. 2024HV-BEV: Decoupling Horizontal and Vertical Feature Sampling for Multi-View 3D Object Detectioncited by 3
  3. 2025HeightFormer: Learning Height Prediction in Voxel Features for Roadside Vision Centric 3D Object Detection via Transformercited by 3
  4. 2025MIC-BEV: Multi-Infrastructure Camera Bird's-Eye-View Transformer with Relation-Aware Fusion for 3D Object Detectioncited by 3
  5. 2026Towards Intrinsic-Aware Monocular 3D Object Detectioncited by 2
  6. 2026DSERT-RoLL: Robust Multi-Modal Perception for Diverse Driving Conditions with Stereo Event-RGB-Thermal Cameras, 4D Radar, and Dual-LiDARcited by 2
  7. 2026Leveraging Previous-Traversal Point Cloud Map Priors for Camera-Based 3D Object Detection and Trackingcited by 2
  8. 2025SimBEV: A Synthetic Multi-Task Multi-Sensor Driving Data Generation Tool and Datasetcited by 1
  9. 2025SABER: Spatially Consistent 3D Universal Adversarial Objects for BEV Detectorscited by 1
  10. 2025OcRFDet: Object-Centric Radiance Fields for Multi-View 3D Object Detection in Autonomous Drivingcited by 1
  11. 2025Neural Rendering for Sensor Adaptation in 3D Object Detectioncited by 1
  12. 2025DenseBEV: Transforming BEV Grid Cells into 3D Objectscited by 1
  13. 2026MASAR: Motion-Appearance Synergy Refinement for Joint Detection and Trajectory Forecastingcited by 1
  14. 2026SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detectioncited by 1
  15. 2025Revisiting Radar Camera Alignment by Contrastive Learning for 3D Object Detectioncited by 0
  16. 2025Automating Infrastructure Surveying: A Framework for Geometric Measurements and Compliance Assessment Using Point Cloud Datacited by 0
  17. 2025DySS: Dynamic Queries and State-Space Learning for Efficient 3D Object Detection from Multi-Camera Videoscited by 0
  18. 2026SDCM: Simulated Densifying and Compensatory Modeling Fusion for Radar-Vision 3-D Object Detection in Internet of Vehiclescited by 0
  19. 2026Efficient Multi-View 3D Object Detection by Dynamic Token Selection and Fine-Tuningcited by 0
  20. 2026SimPB++: Simultaneously Detecting 2D and 3D Objects from Multiple Camerascited by 0
  21. 2026Horizon3D: Sparse Radar-Camera Fusion for Long-Range 3D Perception in Autonomous Drivingcited by 0
  22. 2026Leveraging Vision-Based Point Cloud Map Priors for Camera-Based 3D Object Detection and Online Vectorized HD Mappingcited by 0
  23. 2026MapLightning: Online Vectorized HD Map Construction with 1D Map Tokenscited by 0