通过改进损失函数和时序融合，提升单目3D车道线检测稳定性。
Temporal-Anchor3DLane: Enhanced 3D Lane Detection with Multi-Task Losses and LSTM Fusion
- 设计多任务损失组合，增强几何约束与分类精度
- 引入轻量LSTM时序模块，使轨迹更平滑连续
- 适合自动驾驶中对车道线长期稳定识别的场景
单目3D车道线检测受深度模糊、遮挡和帧间不稳定性影响较大。基于锚点的方法如Anchor3DLane虽表现良好，但仍存在对回归异常值敏感、全局曲线几何监督弱、多损失平衡难、时序信息利用不足等问题。本文提出Temporal-Anchor3DLane，在Anchor3DLane基础上实现三项改进：(1) 多任务损失优化，包括平衡L1回归、Chamfer点集距离、不确定性加权损失，以及聚焦和Dice损失用于分类与可见性；(2) 轻量级时序LSTM融合模块，替代重型Transformer式时序融合，聚合每锚点跨帧特征；(3) 借鉴ESCOP训练策略，将曲线级监督与时序一致性耦合。在OpenLane数据集上，F1提升6.2，轨迹更平滑，证明小规模架构与损失调整可显著增强3D车道线鲁棒性，无需额外传感器或模型扩容。
原文摘要 · Abstract (English)
Monocular 3D lane detection remains challenging due to depth ambiguity, occlusion, and temporal instability across frames. Anchor-based approaches such as Anchor3DLane have demonstrated strong performance by regressing continuous 3D lane curves from multi-camera surround views. However, the baseline model still exhibits (i) sensitivity to regression outliers, (ii) weak supervision of global curve geometry, (iii) difficulty in balancing multiple loss terms, and (iv) limited exploitation of temporal continuity. We propose Temporal-Anchor3DLane, an enhanced 3D lane detection framework that extends Anchor3DLane with three key contributions: (1) a set of multi-task loss improvements, including Balanced L1 regression, Chamfer point-set distance, and uncertainty-based loss weighting, together with focal and Dice components for classification and visibility; (2) a lightweight Temporal LSTM Fusion module that aggregates per-anchor features across frames, replacing a heavier Transformer-style temporal fusion; and (3) ESCOP-style training refinements that couple curve-level supervision with temporal consistency. On OpenLane, Temporal-Anchor3DLane improves F1 by +6.2 and yields smoother temporal trajectories, showing that small architectural and loss refinements significantly enhance 3D lane robustness without extra sensors or scaling.
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。