Polar Parametrization for Vision-based Surround-View 3D Detection

TL;DR

This paper introduces Polar Parametrization, a novel approach for surround-view 3D detection that reformulates key components in polar coordinates, leveraging view symmetry to improve performance and optimize detection in autonomous driving systems.

Contribution

It proposes Polar Parametrization for 3D detection and introduces PolarDETR, a transformer-based model that achieves state-of-the-art results on the nuScenes benchmark.

Findings

PolarDETR ranks 1st on nuScenes leaderboard for 3D detection and tracking.

Polar Parametrization improves optimization and performance by exploiting view symmetry.

The method achieves a promising balance between detection accuracy and computational efficiency.

Abstract

3D detection based on surround-view camera system is a critical technique in autopilot. In this work, we present Polar Parametrization for 3D detection, which reformulates position parametrization, velocity decomposition, perception range, label assignment and loss function in polar coordinate system. Polar Parametrization establishes explicit associations between image patterns and prediction targets, exploiting the view symmetry of surround-view cameras as inductive bias to ease optimization and boost performance. Based on Polar Parametrization, we propose a surround-view 3D DEtection TRansformer, named PolarDETR. PolarDETR achieves promising performance-speed trade-off on different backbone configurations. Besides, PolarDETR ranks 1st on the leaderboard of nuScenes benchmark in terms of both 3D detection and 3D tracking at the submission time (Mar. 4th, 2022). Code will be released at \url{https://github.com/hustvl/PolarDETR}.