M3TR统一处理真实道路地图的各类变化，提升自动驾驶地图更新效率。
M3TR: A Generalist Model for Real-World HD Map Completion
- 采用多掩码机制增强数据，实现无先验时的鲁棒地图补全。
- 在无先验情况下提升1.4 mAP，有先验时比现有方法高4.3 mAP。
- 首个可部署于真实场景的通用地图补全模型，适合自动驾驶系统应用。
自动驾驶依赖高清地图运行，但离线地图易过时。为此，在线地图构建方法利用实时传感器数据推断地图信息。研究表明，地图中多数区域长期不变，可作为先验。本文提出M3TR（多掩码地图变换器），一种无需离线地图先验即可完成地图补全的通用模型。针对Argoverse 2和nuScenes数据集标注不足的问题，我们构建了首个全面的高清地图补全基准。不同于仅针对特定地图变化的专家模型（部署不现实），本模型可统一处理各类变化，性能媲美专家模型。通过地图掩码增强策略，即使无先验也实现+1.4 mAP提升。充分使用先验元素并优化查询设计后，相较现有方法提升+4.3 mAP，成为首个可实际部署的离线先验模型。代码已开源。
原文摘要 · Abstract (English)
Autonomous vehicles rely on HD maps for their operation, but offline HD maps eventually become outdated. For this reason, online HD map construction methods use live sensor data to infer map information instead. Research on real map changes shows that oftentimes entire parts of an HD map remain unchanged and can be used as a prior. We therefore introduce M3TR (Multi-Masking Map Transformer), a generalist approach for HD map completion both with and without offline HD map priors. As a necessary foundation, we address shortcomings in ground truth labels for Argoverse 2 and nuScenes and propose the first comprehensive benchmark for HD map completion. Unlike existing models that specialize in a single kind of map change, which is unrealistic for deployment, our Generalist model handles all kinds of changes, matching the effectiveness of Expert models. With our map masking as augmentation regime, we can even achieve a +1.4 mAP improvement without a prior. Finally, by fully utilizing prior HD map elements and optimizing query designs, M3TR outperforms existing methods by +4.3 mAP while being the first real-world deployable model for offline HD map priors. Code is available at https://github.com/immel-f/m3tr
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。