mlsanityData to 14 Oct 2026

PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images

arXiv 2206.01256 ↗First posted 2 Jun 2022cs.CVcited by 352

Not on the map. Why?

Cited by 25 in End-to-end autonomous driving, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In this paper, we propose PETRv2, a unified framework for 3D perception from multi-view images. Based on PETR, PETRv2 explores the effectiveness of temporal modeling, which utilizes the temporal information of previous frames to boost 3D object detection. More specifically, we extend the 3D position embedding (3D PE) in PETR for temporal modeling. The 3D PE achieves the temporal alignment on object position of different frames. A feature-guided position encoder is further introduced to improve the data adaptability of 3D PE. To support for multi-task learning (e.g., BEV segmentation and 3D lane detection), PETRv2 provides a simple yet effective solution by introducing task-specific queries, which are initialized under different spaces. PETRv2 achieves state-of-the-art performance on 3D object detection, BEV segmentation and 3D lane detection. Detailed robustness analysis is also conducted on PETR framework. We hope PETRv2 can serve as a strong baseline for 3D perception. Code is available at urlhttps://github.com/megvii-research/PETR.

Key facts. Cited by 352 papers in the map (data through 14 Oct 2026). Builds on 48 of its 60 references that are in the map. First posted on arXiv 2 Jun 2022.

Builds on

48 of 60 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  6. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  7. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  8. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  9. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  10. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  11. 2019Objects as Pointscited by 1,175
  12. 2020Center-based 3D Object Detection and Trackingcited by 1,144
36 more
  1. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
  2. 2017Focal Loss for Dense Object Detectioncited by 752
  3. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 713
  4. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  5. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 573
  6. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 552
  7. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 488
  8. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 447
  9. 2021Conditional DETR for Fast Training Convergencecited by 424
  10. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  11. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 341
  12. 2020Conditional Convolutions for Instance Segmentationcited by 314
  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. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  18. 2021FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Camerascited by 239
  19. 2021Efficiently Identifying Task Groupings for Multi-Task Learningcited by 222
  20. 2019Disentangling Monocular 3D Object Detectioncited by 217
  21. 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 201
  22. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 191
  23. 2022BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Drivingcited by 191
  24. 2019Cross-view Semantic Segmentation for Sensing Surroundingscited by 174
  25. 2021Instances as Queriescited by 158
  26. 2021ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detectioncited by 157
  27. 2022M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representationcited by 156
  28. 2022PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmarkcited by 140
  29. 2022BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigscited by 123
  30. 20183D-LaneNet: End-to-End 3D Multiple Lane Detectioncited by 107
  31. 2019Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstructioncited by 106
  32. 2021CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolutioncited by 95
  33. 2020Gen-LaneNet: A Generalized and Scalable Approach for 3D Lane Detectioncited by 75
  34. 2021SOLQ: Segmenting Objects by Learning Queriescited by 68
  35. 2019Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Losscited by 30
  36. 2020DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentationcited by 27

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 31; 2023: 94; 2024: 121; 2025: 68; 2026: 38.

352 papers.

Sort:

By area:

  1. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 572
  2. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 332
  3. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 315
  4. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  5. 2023Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?cited by 242
  6. 2024SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representationcited by 241
  7. 2025MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulationcited by 192
  8. 2024LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awarenesscited by 183
  9. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 178
  10. 2023Panacea: Panoramic and Controllable Video Generation for Autonomous Drivingcited by 168
  11. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 162
  12. 2022DETRs with Hybrid Matchingcited by 150
38 more
  1. 2023SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videoscited by 150
  2. 2025OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoningcited by 143
  3. 2023RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervisioncited by 128
  4. 2022Vision-Centric BEV Perception: A Surveycited by 126
  5. 2025DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Drivingcited by 126
  6. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  7. 2022ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queriescited by 117
  8. 2023PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentationcited by 115
  9. 2023Language Prompt for Autonomous Drivingcited by 111
  10. 2023ADriver-I: A General World Model for Autonomous Drivingcited by 104
  11. 2023FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugincited by 103
  12. 2023Visual Point Cloud Forecasting enables Scalable Autonomous Drivingcited by 99
  13. 2022Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignmentcited by 98
  14. 2023FB-BEV: BEV Representation from Forward-Backward View Transformationscited by 98
  15. 2023Sparse4D v2: Recurrent Temporal Fusion with Sparse Modelcited by 93
  16. 2022BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereocited by 90
  17. 2023Symphonize 3D Semantic Scene Completion with Contextual Instance Queriescited by 90
  18. 2024RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detectioncited by 82
  19. 2023GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformerscited by 79
  20. 2023BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detectioncited by 75
  21. 2023UniPAD: A Universal Pre-training Paradigm for Autonomous Drivingcited by 73
  22. 2023Cross Modal Transformer: Towards Fast and Robust 3D Object Detectioncited by 70
  23. 2023Far3D: Expanding the Horizon for Surround-view 3D Object Detectioncited by 70
  24. 2023Sparse4D v3: Advancing End-to-End 3D Detection and Trackingcited by 70
  25. 2022BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detectioncited by 66
  26. 2023Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perceptioncited by 65
  27. 2023Fully Sparse 3D Occupancy Predictioncited by 64
  28. 2024OPUS: Occupancy Prediction Using a Sparse Setcited by 56
  29. 2023Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Trackingcited by 54
  30. 2024FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird's-Eye View and Perspective Viewcited by 51
  31. 2023Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Constructioncited by 50
  32. 2024Context and Geometry Aware Voxel Transformer for Semantic Scene Completioncited by 50
  33. 2023Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Predictioncited by 49
  34. 2023OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queriescited by 48
  35. 2024SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Drivingcited by 47
  36. 2023LATR: 3D Lane Detection from Monocular Images with Transformercited by 44
  37. 2024Stream Query Denoising for Vectorized HD Map Constructioncited by 43
  38. 2023TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoningcited by 41

50 most cited of 352 All 352 (JSON)