mlsanityData to 14 Oct 2026

Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detection

arXiv 2407.15354 ↗First posted 22 Jul 2024cs.CV cs.ROcited by 4

Not on the map. Why?

Abstract (arXiv)

The Bird's-Eye-View (BEV) representation is a critical factor that directly impacts the 3D object detection performance, but the traditional BEV grid representation induces quadratic computational cost as the spatial resolution grows. To address this limitation, we present a new camera-based 3D object detector with high-resolution vector representation: VectorFormer. The presented high-resolution vector representation is combined with the lower-resolution BEV representation to efficiently exploit 3D geometry from multi-camera images at a high resolution through our two novel modules: vector scattering and gathering. To this end, the learned vector representation with richer scene contexts can serve as the decoding query for final predictions. We conduct extensive experiments on the nuScenes dataset and demonstrate state-of-the-art performance in NDS and inference time. Furthermore, we investigate query-BEV-based methods incorporated with our proposed vector representation and observe a consistent performance improvement.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 54 of its 58 references that are in the map. First posted on arXiv 22 Jul 2024.

Builds on

54 of 58 references.

References · 54

  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. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  6. 2022A ConvNet for the 2020scited by 3,579
  7. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  8. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  9. 2017Deformable Convolutional Networkscited by 1,488
  10. 2015Spatial Transformer Networkscited by 1,429
  11. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  12. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
38 more
  1. 2019Objects as Pointscited by 1,175
  2. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
  3. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  4. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 746
  5. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 713
  6. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  7. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 572
  8. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 552
  9. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 488
  10. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 447
  11. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 409
  12. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 352
  13. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  14. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 341
  15. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 315
  16. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  17. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  18. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 249
  19. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  20. 2019An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detectioncited by 163
  21. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 162
  22. 2022DETRs with Hybrid Matchingcited by 150
  23. 2023SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videoscited by 150
  24. 2022Vision-Centric BEV Perception: A Surveycited by 126
  25. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  26. 2021Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsitycited by 98
  27. 2023FB-BEV: BEV Representation from Forward-Backward View Transformationscited by 98
  28. 2023Sparse4D v2: Recurrent Temporal Fusion with Sparse Modelcited by 93
  29. 2022Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformercited by 80
  30. 2022BEVPoolv2: A Cutting-edge Implementation of BEVDet Toward Deploymentcited by 79
  31. 2023Sparse4D v3: Advancing End-to-End 3D Detection and Trackingcited by 70
  32. 2021PnP-DETR: Towards Efficient Visual Analysis with Transformerscited by 52
  33. 2023BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detectioncited by 35
  34. 2023SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detectioncited by 30
  35. 2022MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbonescited by 29
  36. 2022LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detectioncited by 27
  37. 2022Vision-based Uneven BEV Representation Learning with Polar Rasterization and Surface Estimationcited by 23
  38. 2022DETR4D: Direct Multi-View 3D Object Detection with Sparse Attentioncited by 21

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detectorcited by 6
  2. 2026Towards Intrinsic-Aware Monocular 3D Object Detectioncited by 4
  3. 2025OcRFDet: Object-Centric Radiance Fields for Multi-View 3D Object Detection in Autonomous Drivingcited by 1
  4. 2025Dual-Domain Homogeneous Fusion with Cross-Modal Mamba and Progressive Decoder for 3D Object Detectioncited by 0