mlsanityData to 7 Oct 2026

3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection Transformers

arXiv 2211.14710 ↗First posted 27 Nov 2022cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Transformer-based methods have swept the benchmarks on 2D and 3D detection on images. Because tokenization before the attention mechanism drops the spatial information, positional encoding becomes critical for those methods. Recent works found that encodings based on samples of the 3D viewing rays can significantly improve the quality of multi-camera 3D object detection. We hypothesize that 3D point locations can provide more information than rays. Therefore, we introduce 3D point positional encoding, 3DPPE, to the 3D detection Transformer decoder. Although 3D measurements are not available at the inference time of monocular 3D object detection, 3DPPE uses predicted depth to approximate the real point positions. Our hybriddepth module combines direct and categorical depth to estimate the refined depth of each pixel. Despite the approximation, 3DPPE achieves 46.0 mAP and 51.4 NDS on the competitive nuScenes dataset, significantly outperforming encodings based on ray samples. We make the codes available at https://github.com/drilistbox/3DPPE.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 31 of its 36 references that are in the map. First posted on arXiv 27 Nov 2022.

Builds on

31 of 36 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  5. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  6. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  7. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  8. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  9. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  10. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  11. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  12. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
19 more
  1. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  2. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 486
  3. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  4. 2021Conditional DETR for Fast Training Convergencecited by 422
  5. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
  6. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 351
  7. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  8. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  9. 2022FUTR3D: A Unified Sensor Fusion Framework for 3D Detectioncited by 194
  10. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 190
  11. 2021Fast Convergence of DETR with Spatially Modulated Co-Attentioncited by 176
  12. 2020Rethinking Transformer-based Set Prediction for Object Detectioncited by 156
  13. 2021Efficient DETR: Improving End-to-End Object Detector with Dense Priorcited by 128
  14. 2018In Defense of Classical Image Processing: Fast Depth Completion on the CPUcited by 96
  15. 2022Accelerating DETR Convergence via Semantic-Aligned Matchingcited by 58
  16. 2022STS: Surround-view Temporal Stereo for Multi-view 3D Detectioncited by 53
  17. 2022Learning Ego 3D Representation as Ray Tracingcited by 43
  18. 2021Anchor DETR: Query Design for Transformer-Based Object Detectioncited by 30
  19. 2022D3ETR: Decoder Distillation for Detection Transformercited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 4; 2025: 5; 2026: 3.

15 papers.

Sort:

By area:

  1. 2023FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugincited by 101
  2. 2023UniPAD: A Universal Pre-training Paradigm for Autonomous Drivingcited by 73
  3. 2023PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigmcited by 56
  4. 2024VisionPAD: A Vision-Centric Pre-training Paradigm for Autonomous Drivingcited by 15
  5. 2024SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objectscited by 12
  6. 2025CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detectorcited by 4
  7. 2025FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detectioncited by 2
  8. 2025Accelerate 3D Object Detection Models via Zero-Shot Attention Key Pruningcited by 2
  9. 2026Towards Intrinsic-Aware Monocular 3D Object Detectioncited by 2
  10. 2024UltimateDO: An Efficient Framework to Marry Occupancy Prediction with 3D Object Detection via Channel2heightcited by 1
  11. 2024SPformer: A Transformer Based DRL Decision Making Method for Connected Automated Vehiclescited by 1
  12. 2026Training-free Spatially Grounded Geometric Shape Encoding (Technical Report)cited by 1
3 more
  1. 2025FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detectioncited by 0
  2. 2025A Three-Level Alignment Framework for Large-Scale 3D Retrieval and Controlled 4D Generationcited by 0
  3. 2026BEV-Denoise: Learning Intrinsic Noise for Accurate Bird's-Eye-View Semantic Segmentationcited by 0