通过时空交互提升自动驾驶矢量地图构建精度
InteractionMap: Improving Online Vectorized HDMap Construction with Interaction
- 引入点到实例的位置关系先验，利用地图元素的形状特性
- 基于关键帧的分层时序融合，实现局部到全局的时间信息交互
- 几何感知分类损失与匹配代价，解决语义与几何分布错位问题
矢量化高精地图对自动驾驶系统至关重要。当前主流方法多采用类似DETR的框架端到端生成地图。本文提出InteractionMap，通过充分挖掘时空维度的局部到全局信息交互，改进现有方法。首先，在点级到实例级引入显式位置关系先验，利用地图元素的强形状先验。其次，设计基于关键帧的分层时序融合模块，实现从局部到全局的时序信息交互。最后，针对分类与回归分支导致的输出分布错位问题，通过引入几何感知分类损失和几何感知匹配代价，实现语义与几何信息的交互。在nuScenes和Argoverse2两个基准上均达到领先性能。
原文摘要 · Abstract (English)
Vectorized high-definition (HD) maps are essential for an autonomous driving system. Recently, state-of-the-art map vectorization methods are mainly based on DETR-like framework to generate HD maps in an end-to-end manner. In this paper, we propose InteractionMap, which improves previous map vectorization methods by fully leveraging local-to-global information interaction in both time and space. Firstly, we explore enhancing DETR-like detectors by explicit position relation prior from point-level to instance-level, since map elements contain strong shape priors. Secondly, we propose a key-frame-based hierarchical temporal fusion module, which interacts temporal information from local to global. Lastly, the separate classification branch and regression branch lead to the problem of misalignment in the output distribution. We interact semantic information with geometric information by introducing a novel geometric-aware classification loss in optimization and a geometric-aware matching cost in label assignment. InteractionMap achieves state-of-the-art performance on both nuScenes and Argoverse2 benchmarks.
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。