PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection

TL;DR

PARTNER introduces a novel polar coordinate-based 3D object detector that addresses feature distortion issues, improving performance and robustness in LiDAR-based detection tasks, especially in streaming and multi-resolution scenarios.

Contribution

It proposes global representation re-alignment and instance-level geometric info integration to enhance polar-based 3D detection accuracy.

Findings

Outperforms previous polar-based methods by 3.68% on Waymo

Achieves 9.15% improvement on ONCE dataset

Excels in streaming-based detection and multi-resolution settings

Abstract

Recently, polar-based representation has shown promising properties in perceptual tasks. In addition to Cartesian-based approaches, which separate point clouds unevenly, representing point clouds as polar grids has been recognized as an alternative due to (1) its advantage in robust performance under different resolutions and (2) its superiority in streaming-based approaches. However, state-of-the-art polar-based detection methods inevitably suffer from the feature distortion problem because of the non-uniform division of polar representation, resulting in a non-negligible performance gap compared to Cartesian-based approaches. To tackle this issue, we present PARTNER, a novel 3D object detector in the polar coordinate. PARTNER alleviates the dilemma of feature distortion with global representation re-alignment and facilitates the regression by introducing instance-level geometric information into the detection head. Extensive experiments show overwhelming advantages in streaming-based detection and different resolutions. Furthermore, our method outperforms the previous polar-based works with remarkable margins of 3.68% and 9.15% on Waymo and ONCE validation set, thus achieving competitive results over the state-of-the-art methods.