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

arXiv: https://arxiv.org/abs/2211.14710 · HTML: https://mlsanity.com/paper/2211.14710/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 36 references that are in the map.
- First posted on arXiv 27 Nov 2022.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://mlsanity.com/paper/2206.10092/) (2022)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [DN-DETR: Accelerate DETR Training by Introducing Query DeNoising](https://mlsanity.com/paper/2203.01305/) (2022)
- [FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection](https://mlsanity.com/paper/2104.10956/) (2021)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images](https://mlsanity.com/paper/2206.01256/) (2022)
- [BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection](https://mlsanity.com/paper/2203.17054/) (2022)
- [Is Pseudo-Lidar needed for Monocular 3D Object detection?](https://mlsanity.com/paper/2108.06417/) (2021)
- [FUTR3D: A Unified Sensor Fusion Framework for 3D Detection](https://mlsanity.com/paper/2203.10642/) (2022)
- [Probabilistic and Geometric Depth: Detecting Objects in Perspective](https://mlsanity.com/paper/2107.14160/) (2021)
- [Fast Convergence of DETR with Spatially Modulated Co-Attention](https://mlsanity.com/paper/2101.07448/) (2021)
- [Rethinking Transformer-based Set Prediction for Object Detection](https://mlsanity.com/paper/2011.10881/) (2020)
- [Efficient DETR: Improving End-to-End Object Detector with Dense Prior](https://mlsanity.com/paper/2104.01318/) (2021)
- [In Defense of Classical Image Processing: Fast Depth Completion on the CPU](https://mlsanity.com/paper/1802.00036/) (2018)
- [Accelerating DETR Convergence via Semantic-Aligned Matching](https://mlsanity.com/paper/2203.06883/) (2022)
- [STS: Surround-view Temporal Stereo for Multi-view 3D Detection](https://mlsanity.com/paper/2208.10145/) (2022)
- [Learning Ego 3D Representation as Ray Tracing](https://mlsanity.com/paper/2206.04042/) (2022)
- [Anchor DETR: Query Design for Transformer-Based Object Detection](https://mlsanity.com/paper/2109.07107/) (2021)

## Built on by (most cited first, 15 of 15)

- [FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugin](https://mlsanity.com/paper/2311.12058/) (2023)
- [UniPAD: A Universal Pre-training Paradigm for Autonomous Driving](https://mlsanity.com/paper/2310.08370/) (2023)
- [PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm](https://mlsanity.com/paper/2310.08586/) (2023)
- [VisionPAD: A Vision-Centric Pre-training Paradigm for Autonomous Driving](https://mlsanity.com/paper/2411.14716/) (2024)
- [SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects](https://mlsanity.com/paper/2403.20318/) (2024)
- [CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector](https://mlsanity.com/paper/2508.11185/) (2025)
- [Towards Intrinsic-Aware Monocular 3D Object Detection](https://mlsanity.com/paper/2603.27059/) (2026)
- [FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2502.15488/) (2025)
- [Accelerate 3D Object Detection Models via Zero-Shot Attention Key Pruning](https://mlsanity.com/paper/2503.08101/) (2025)
- [UltimateDO: An Efficient Framework to Marry Occupancy Prediction with 3D Object Detection via Channel2height](https://mlsanity.com/paper/2409.11160/) (2024)
- [SPformer: A Transformer Based DRL Decision Making Method for Connected Automated Vehicles](https://mlsanity.com/paper/2409.15105/) (2024)
- [Training-free Spatially Grounded Geometric Shape Encoding (Technical Report)](https://mlsanity.com/paper/2604.07522/) (2026)
- [FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2511.09347/) (2025)
- [A Three-Level Alignment Framework for Large-Scale 3D Retrieval and Controlled 4D Generation](https://mlsanity.com/paper/2512.22294/) (2025)
- [BEV-Denoise: Learning Intrinsic Noise for Accurate Bird's-Eye-View Semantic Segmentation](https://mlsanity.com/paper/2606.22931/) (2026)

## 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.