mlsanityData to 14 Oct 2026

CAPE: Camera View Position Embedding for Multi-View 3D Object Detection

arXiv 2303.10209 ↗First posted 17 Mar 2023cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

In this paper, we address the problem of detecting 3D objects from multi-view images. Current query-based methods rely on global 3D position embeddings (PE) to learn the geometric correspondence between images and 3D space. We claim that directly interacting 2D image features with global 3D PE could increase the difficulty of learning view transformation due to the variation of camera extrinsics. Thus we propose a novel method based on CAmera view Position Embedding, called CAPE. We form the 3D position embeddings under the local camera-view coordinate system instead of the global coordinate system, such that 3D position embedding is free of encoding camera extrinsic parameters. Furthermore, we extend our CAPE to temporal modeling by exploiting the object queries of previous frames and encoding the ego-motion for boosting 3D object detection. CAPE achieves state-of-the-art performance (61.0% NDS and 52.5% mAP) among all LiDAR-free methods on nuScenes dataset. Codes and models are available on hrefhttps://github.com/PaddlePaddle/Paddle3DPaddle3D and hrefhttps://github.com/kaixinbear/CAPEPyTorch Implementation.

Key facts. Cited by 40 papers in the map (data through 14 Oct 2026). Builds on 46 of its 54 references that are in the map. First posted on arXiv 17 Mar 2023.

Builds on

46 of 54 references.

References · 46

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  5. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  6. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,319
  7. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  8. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
  9. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  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. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
34 more
  1. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 573
  2. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 572
  3. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 552
  4. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 488
  5. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 457
  6. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 447
  7. 2021Conditional DETR for Fast Training Convergencecited by 424
  8. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 410
  9. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 368
  10. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 352
  11. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 341
  12. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 327
  13. 20163D Bounding Box Estimation Using Deep Learning and Geometrycited by 278
  14. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  15. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 252
  16. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 249
  17. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 202
  18. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 191
  19. 2020Predicting Semantic Map Representations from Images using Pyramid Occupancy Networkscited by 175
  20. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 156
  21. 2020RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Drivingcited by 150
  22. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  23. 2019LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Drivingcited by 133
  24. 2020Rethinking Pseudo-LiDAR Representationcited by 109
  25. 2019TANet: Robust 3D Object Detection from Point Clouds with Triple Attentioncited by 108
  26. 2019GS3D: An Efficient 3D Object Detection Framework for Autonomous Drivingcited by 106
  27. 2022BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereocited by 90
  28. 2021Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detectioncited by 84
  29. 2020End-to-End Pseudo-LiDAR for Image-Based 3D Object Detectioncited by 80
  30. 2022MonoDistill: Learning Spatial Features for Monocular 3D Object Detectioncited by 68
  31. 2021Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detectioncited by 67
  32. 2022GitNet: Geometric Prior-based Transformation for Birds-Eye-View Segmentationcited by 24
  33. 2021Exploring Geometric Consistency for Monocular 3D Object Detectioncited by 17
  34. 2022AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perceptioncited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 16; 2025: 9; 2026: 7.

40 papers.

Sort:

By area:

  1. 2023Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenescited by 191
  2. 2024Towards learning-based planning:The nuPlan benchmark for real-world autonomous drivingcited by 104
  3. 2023DrivingDiffusion: Layout-Guided multi-view driving scene video generation with latent diffusion modelcited by 75
  4. 2024Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysiscited by 53
  5. 2023PointBeV: A Sparse Approach to BeV Predictionscited by 23
  6. 2025GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generationcited by 23
  7. 2023ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Boxcited by 20
  8. 2024OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networkscited by 17
  9. 2023Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detectioncited by 13
  10. 20243DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for Indoor 3D Object Detectioncited by 13
  11. 2024Enhancing 3D Object Detection with 2D Detection-Guided Query Anchorscited by 12
  12. 2024SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objectscited by 12
28 more
  1. 2023OCBEV: Object-Centric BEV Transformer for Multi-View 3D Object Detectioncited by 10
  2. 2025Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous Drivingcited by 10
  3. 2024DualBEV: Unifying Dual View Transformation with Probabilistic Correspondencescited by 9
  4. 2024Make Your ViT-based Multi-view 3D Detectors Faster via Token Compressioncited by 9
  5. 2026VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detectioncited by 9
  6. 2025RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embeddingcited by 7
  7. 2023Diffusion-based 3D Object Detection with Random Boxescited by 5
  8. 2024WidthFormer: Toward Efficient Transformer-based BEV View Transformationcited by 5
  9. 2024DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perceptioncited by 5
  10. 2024PoIFusion: Multi-Modal 3D Object Detection via Fusion at Points of Interestcited by 4
  11. 2024You Only Look Bottom-Up for Monocular 3D Object Detectioncited by 3
  12. 2024DuoSpaceNet: Leveraging Both Bird's-Eye-View and Perspective View Representations for 3D Object Detectioncited by 2
  13. 2025FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformerscited by 2
  14. 2024DVPE: Divided View Position Embedding for Multi-View 3D Object Detectioncited by 1
  15. 2024QuadBEV: An Efficient Quadruple-Task Perception Framework via Bird's-Eye-View Representationcited by 1
  16. 2024Learning Content-Aware Multi-Modal Joint Input Pruning via Bird's-Eye-View Representationcited by 1
  17. 2025SimBEV: A Synthetic Multi-Task Multi-Sensor Driving Data Generation Tool and Datasetcited by 1
  18. 2025Compressed Map Priors for 3D Perceptioncited by 1
  19. 2023Towards Efficient 3D Object Detection in Bird's-Eye-View Space for Autonomous Driving: A Convolutional-Only Approachcited by 0
  20. 2025Pseudo-Label Guided Real-World Image De-weathering: A Learning Framework with Imperfect Supervisioncited by 0
  21. 2025RCDINO: Enhancing Radar-Camera 3D Object Detection with DINOv2 Semantic Featurescited by 0
  22. 2025DynaPose4D: High-Quality 4D Dynamic Content Generation via Pose Alignment Losscited by 0
  23. 2026Effective Multi-sensor Conditioning for Street-view Novel-view Synthesiscited by 0
  24. 2026BEV-Denoise: Learning Intrinsic Noise for Accurate Bird's-Eye-View Semantic Segmentationcited by 0
  25. 2026GaussianDWM++: Language-Grounded 3D Gaussian Driving World Model for Unified Scene Understanding, Editing, and Multi-Modal Generationcited by 0
  26. 2026GRACE: Geometry- and Ray-Aware Camera-Efficient Multi-View Pedestrian Trackingcited by 0
  27. 2026PQR3D: Progressive Query Refinement over Reference-Conditioned Temporal Windows for Multi-View 3D Object Detectioncited by 0
  28. 2026Feedforward Novel View Synthesis for Heterogeneous Camerascited by 0