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

Source: [3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection Transformers](<https://www.sota2.com/research/paper/68fa702b1e209131cea498d2>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:00.298Z

Authors: Changyong Shu, JIajun Deng, Fisher Yu, Yifan Liu

Published: 2022-11-27T03:36:32.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Object Detection on nuScenes (val)](<https://www.sota2.com/research/sota/object-detection-on-nuscenes-val.md>): Object Detection; nuScenes (val); mAP: 39.1.

- [3D Object Detection on nuScenes (test)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-test.md>): 3D Object Detection; nuScenes (test); mAP: 46.

- [3D Object Detection on nuScenes (val)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-val.md>): 3D Object Detection; nuScenes (val); NDS: 45.8.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2211.14710>)

[PDF](<https://arxiv.org/pdf/2211.14710.pdf>)