PETR: Position Embedding Transformation for Multi-view 3D Object Detection

In this paper, we develop position embedding transformation (PETR) for multi-view 3D object detection. PETR encodes the position information of 3D coordinates into image features, producing the 3D position-aware features. Object query can perceive the 3D position-aware features and perform end-to-en...

Full description

Saved in:
Bibliographic Details
Published inComputer Vision - ECCV 2022 Vol. 13687; pp. 531 - 548
Main Authors Liu, Yingfei, Wang, Tiancai, Zhang, Xiangyu, Sun, Jian
Format Book Chapter
LanguageEnglish
Published Switzerland Springer 2022
Springer Nature Switzerland
SeriesLecture Notes in Computer Science
Subjects
3D object detection
Position embedding
Transformer
Online AccessGet full text

Cover

More Information
Summary:In this paper, we develop position embedding transformation (PETR) for multi-view 3D object detection. PETR encodes the position information of 3D coordinates into image features, producing the 3D position-aware features. Object query can perceive the 3D position-aware features and perform end-to-end object detection. PETR achieves state-of-the-art performance (50.4% NDS and 44.1% mAP) on standard nuScenes dataset and ranks 1st place on the benchmark. It can serve as a simple yet strong baseline for future research. Code is available at https://github.com/megvii-research/PETR.
Bibliography:Y. Liu and T. Wang—Equal contribution.
ISBN:9783031198113
3031198115
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-031-19812-0_31