AMap：蒸馏未来先验的前瞻感知在线高精地图构建
AMap: Distilling Future Priors for Ahead-Aware Online HD Map Construction
把「未来帧教师 + 当前帧学生」的蒸馏范式引入在线建图，用多层鸟瞰图蒸馏加空间掩码和非对称查询适配，让单帧模型零推理开销获得前瞻能力；对做自动驾驶感知、时序融合和特权信息蒸馏的视觉研究者可直接复用。
原文依据 we propose AMap, a novel framework for Ahead-aware online HD Mapping
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在线高精地图构建对自动驾驶至关重要。近期方法借助历史时序融合提升性能，但我们发现该范式存在一个关键安全缺陷：它本质上是「空间后视」的。这些方法主要改善已行驶区域的地图重建，对前方未知道路的提升十分有限。更重要的是，我们对下游规划任务的分析揭示出一种严重的不对称性：后方感知误差通常可以容忍，而前方区域的不准确会直接引发危险的驾驶操作。为弥合这一安全缺口，我们提出 AMap，一种面向前瞻感知在线高精地图构建的新框架。我们开创了「从未来蒸馏」范式：由可获取未来时序上下文的特权教师模型，指导仅限当前帧的轻量学生模型。该过程将前瞻性知识隐式压缩进学生模型，使其在零推理开销下具备「前瞻」能力。技术上，我们提出带空间掩码的多层级鸟瞰图蒸馏策略，以及非对称查询适配模块，从而有效地将未来感知表征迁移到学生的静态查询上。在 nuScenes 与 Argoverse 2 基准上的大量实验表明，AMap 显著增强了当前帧感知。最值得注意的是，它在关键前方区域超越了最优的时序模型，同时保持当前帧推理的效率。
英文原文摘要 1551 字符
Online High-Definition (HD) map construction is pivotal for autonomous driving. While recent approaches leverage historical temporal fusion to improve performance, we identify a critical safety flaw in this paradigm: it is inherently "spatially backward-looking." These methods predominantly enhance map reconstruction in traversed areas, offering minimal improvement for the unseen road ahead. Crucially, our analysis of downstream planning tasks reveals a severe asymmetry: while rearward perception errors are often tolerable, inaccuracies in the forward region directly precipitate hazardous driving maneuvers. To bridge this safety gap, we propose AMap, a novel framework for Ahead-aware online HD Mapping. We pioneer a "distill-from-future" paradigm, where a teacher model with privileged access to future temporal contexts guides a lightweight student model restricted to the current frame. This process implicitly compresses prospective knowledge into the student model, endowing it with "look-ahead" capabilities at zero inference-time cost. Technically, we introduce a Multi-Level BEV Distillation strategy with spatial masking and an Asymmetric Query Adaptation module to effectively transfer future-aware representations to the student's static queries. Extensive experiments on the nuScenes and Argoverse 2 benchmark demonstrate that AMap significantly enhances current-frame perception. Most notably, it outperforms state-of-the-art temporal models in critical forward regions while maintaining the efficiency of current-frame inference.