PolarFormer: Multi-camera 3D Object Detection with Polar Transformer

30 Jun 2022  ·  Yanqin Jiang, Li Zhang, Zhenwei Miao, Xiatian Zhu, Jin Gao, Weiming Hu, Yu-Gang Jiang ·

3D object detection in autonomous driving aims to reason "what" and "where" the objects of interest present in a 3D world. Following the conventional wisdom of previous 2D object detection, existing methods often adopt the canonical Cartesian coordinate system with perpendicular axis. However, we conjugate that this does not fit the nature of the ego car's perspective, as each onboard camera perceives the world in shape of wedge intrinsic to the imaging geometry with radical (non-perpendicular) axis. Hence, in this paper we advocate the exploitation of the Polar coordinate system and propose a new Polar Transformer (PolarFormer) for more accurate 3D object detection in the bird's-eye-view (BEV) taking as input only multi-camera 2D images. Specifically, we design a cross attention based Polar detection head without restriction to the shape of input structure to deal with irregular Polar grids. For tackling the unconstrained object scale variations along Polar's distance dimension, we further introduce a multi-scalePolar representation learning strategy. As a result, our model can make best use of the Polar representation rasterized via attending to the corresponding image observation in a sequence-to-sequence fashion subject to the geometric constraints. Thorough experiments on the nuScenes dataset demonstrate that our PolarFormer outperforms significantly state-of-the-art 3D object detection alternatives.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Robust Camera Only 3D Object Detection nuScenes-C PolarFormer (r101) mean Corruption Error (mCE) 96.06 # 2
mean Resilience Rate (mRR) 70.88 # 1
Robust Camera Only 3D Object Detection nuScenes-C PolarFormer (vov) mean Corruption Error (mCE) 98.75 # 5
mean Resilience Rate (mRR) 67.51 # 7
3D Object Detection nuScenes Camera Only PolarFormer NDS 57.2 # 15
Future Frame false # 1

Methods