发表机构
Purdue University（普渡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出可控道路标线生成方法，利用文本条件扩散模型和结构化高斯渲染，从可行驶区域掩膜合成标线布局，在Argoverse 2和Waymo数据集上显著优于基线。
AI 中文摘要
车道和道路标线为车辆导航和多智能体协调提供关键引导，然而大规模制作标线仍依赖人工流程，这限制了定量分析和场景测试。我们提出可控道路标线生成方法，该方法从可行驶区域掩膜、可选的外圈标线和文本描述中合成缺失的中心区域标线布局。我们的基准使用确定性的、基于元数据的提示词和三个输出通道：车道分隔线、道路分隔线和人行横道。我们开发了一个条件鸟瞰图（BEV）流程，结合了（i）使用拓扑感知辅助损失训练的文本条件潜在修正流DiT，（ii）高斯模糊的训练目标，以稳定细薄稀疏标线的学习，以及（iii）结构化高斯渲染（SGR），一种无需训练的后处理过程，通过提取折线、拟合三次贝塞尔曲线并将其重新渲染为各向异性超高斯基元来恢复清晰的分隔线几何形状。在4,597个Argoverse 2测试瓦片上，我们的系统实现了80.8的Buffered F1和50.2的clDice，而适配的最先进掩膜细化基线为38.8和24.6。在Waymo数据集上，它产生了88.0的Buffered F1和66.2的clDice。组件消融实验显示，拓扑感知监督和SGR带来了互补的连通性增益。文本编辑实验表明，更强的引导提高了编辑成功率，但也增加了对非目标结构的更改。我们认为这一框架是朝着仿真就绪的道路标线变化、自动化地图补全和早期基础设施设计探索迈出的一步。
英文摘要
Lane and road markings provide critical guidance for vehicle navigation and multi-agent coordination, yet authoring them at scale remains a manual workflow that limits quantitative analysis and scenario testing. We introduce Controllable Road Marking Generation, which synthesizes a missing center-region marking layout from a drivable-area mask, optional outer-ring markings, and a textual description. Our benchmark uses deterministic, metadata-derived prompts and three output channels: lane dividers, road dividers, and pedestrian crossings. We develop a conditional bird's-eye-view (BEV) pipeline that combines (i) a text-conditioned latent rectified-flow DiT trained with a topology-aware auxiliary loss, (ii) Gaussian-blurred training targets that stabilize learning of thin, sparse markings, and (iii) Structured Gaussian Render (SGR), a training-free post-process that recovers crisp divider geometry by extracting polylines, fitting cubic Bézier curves, and re-rendering them as anisotropic super-Gaussian primitives. On 4,597 Argoverse~2 test tiles, our system achieves Buffered F1 of 80.8 and clDice of 50.2, compared with 38.8 and 24.6 for an adapted state-of-the-art mask-refinement baseline. On Waymo dataset, it yields 88.0 Buffered F1 and 66.2 clDice. Component ablations show complementary connectivity gains from topology-aware supervision and SGR. Text-editing experiments reveal that stronger guidance improves edit success but also increases changes to non-target structures. We see this framework as a step toward simulation-ready road-marking variation, automated map completion, and early-stage infrastructure design exploration.
