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

03/10/2022

∙

by   Yingfei Liu, et al.

∙

9

∙

share

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 44.1 It can serve as a simple yet strong baseline for future research.