Mask2Map：利用鸟瞰图分割掩码构建矢量化高精地图
Mask2Map: Vectorized HD Map Construction Using Bird's Eye View Segmentation Masks
AI总结：
针对自动驾驶在线高精地图构建需求，提出由IMPNet和MMPNet组成的Mask2Map方法，通过网络间去噪训练解决网络间不一致问题，在nuScenes和Argoverse2基准上mAP分别提升10.1%和4.1。
摘要：
本文提出了一种面向自动驾驶应用的新型端到端在线高精地图构建方法Mask2Map。该方法聚焦于预测场景中地图实例的类别与有序点集，以鸟瞰图（BEV）形式呈现。Mask2Map包含两个核心组件：实例级掩码预测网络（IMPNet）和掩码驱动地图预测网络（MMPNet）。IMPNet生成掩码感知查询（Mask-Aware Queries）与BEV分割掩码，以全局捕获全面的语义信息。随后，MMPNet通过位置查询生成器（PQG）和几何特征提取器（GFE）两个子模块，利用局部上下文信息增强这些查询特征：PQG将BEV位置信息嵌入掩码感知查询，提取实例级位置查询；GFE则利用BEV分割掩码生成点级几何特征。然而我们发现，由于IMPNet与MMPNet在预测结果与真值（GT）匹配方式上存在差异，导致网络间不一致，限制了Mask2Map的性能。为解决这一问题，我们提出网络间去噪训练方法，引导模型对受噪声真值查询和扰动真值分割掩码影响的输出进行去噪。我们在nuScenes和Argoverse2基准上开展评估，结果表明Mask2Map相比现有最优方法实现了显著性能提升，两个基准上的mAP分别提升10.1%和4.1。代码可在https://github.com/SehwanChoi0307/Mask2Map获取。
英文摘要：
In this paper, we introduce Mask2Map, a novel end-to-end online HD map construction method designed for autonomous driving applications. Our approach focuses on predicting the class and ordered point set of map instances within a scene, represented in the bird's eye view (BEV). Mask2Map consists of two primary components: the Instance-Level Mask Prediction Network (IMPNet) and the Mask-Driven Map Prediction Network (MMPNet). IMPNet generates Mask-Aware Queries and BEV Segmentation Masks to capture comprehensive semantic information globally. Subsequently, MMPNet enhances these query features using local contextual information through two submodules: the Positional Query Generator (PQG) and the Geometric Feature Extractor (GFE). PQG extracts instance-level positional queries by embedding BEV positional information into Mask-Aware Queries, while GFE utilizes BEV Segmentation Masks to generate point-level geometric features. However, we observed limited performance in Mask2Map due to inter-network inconsistency stemming from different predictions to Ground Truth (GT) matching between IMPNet and MMPNet. To tackle this challenge, we propose the Inter-network Denoising Training method, which guides the model to denoise the output affected by both noisy GT queries and perturbed GT Segmentation Masks. Our evaluation conducted on nuScenes and Argoverse2 benchmarks demonstrates that Mask2Map achieves remarkable performance improvements over previous state-of-the-art methods, with gains of 10.1% mAP and 4.1 mAP, respectively. Our code can be found at https://github.com/SehwanChoi0307/Mask2Map.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
