Polar Parametrization for Vision-based Surround-View 3D Detection
This addresses the critical problem of accurate 3D perception for autonomous vehicles, offering a novel approach that improves performance in a key domain.
The paper tackles 3D detection for autonomous driving using surround-view cameras by introducing Polar Parametrization, which reformulates key components in polar coordinates to exploit view symmetry, and proposes PolarDETR, achieving state-of-the-art performance on the nuScenes benchmark for both 3D detection and tracking.
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}.