让地图查询学会全局视角，提升高精地图构建精度
Learning Global Representation from Queries for Vectorized HD Map Construction
- 引入全局表示学习模块，让所有查询协同反映整体地图结构
- 在nuScenes和Argoverse2上mAP显著超越现有基线方法
- 适合研究自动驾驶地图构建与视觉感知融合的开发者
在线构建矢量化高精地图是现代自动驾驶系统的核心。当前基于DETR框架的方法将其视为实例检测问题，但依赖独立可学习的物体查询，导致视角局限于局部，忽略了高精地图固有的全局结构。本文提出MapGR（全局表示学习用于高精地图构建），通过两个协同模块实现：全局表示学习（GRL）模块，通过精心设计的整体分割任务引导所有查询更好地对齐全局地图；全局表示引导（GRG）模块，为每个查询显式注入全局上下文信息以优化其定位。在nuScenes和Argoverse2数据集上的评估表明，该方法相比领先基线在平均精度（mAP）上取得显著提升。
原文摘要 · Abstract (English)
The online construction of vectorized high-definition (HD) maps is a cornerstone of modern autonomous driving systems. State-of-the-art approaches, particularly those based on the DETR framework, formulate this as an instance detection problem. However, their reliance on independent, learnable object queries results in a predominantly local query perspective, neglecting the inherent global representation within HD maps. In this work, we propose \textbf{MapGR} (\textbf{G}lobal \textbf{R}epresentation learning for HD \textbf{Map} construction), an architecture designed to learn and utilize a global representations from queries. Our method introduces two synergistic modules: a Global Representation Learning (GRL) module, which encourages the distribution of all queries to better align with the global map through a carefully designed holistic segmentation task, and a Global Representation Guidance (GRG) module, which endows each individual query with explicit, global-level contextual information to facilitate its optimization. Evaluations on the nuScenes and Argoverse2 datasets validate the efficacy of our approach, demonstrating substantial improvements in mean Average Precision (mAP) compared to leading baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。