提出自适应坡度融合与时间一致性框架，提升3D车道线高度估计精度。
SC-Lane: Slope-aware and Consistent Road Height Estimation Framework for 3D Lane Detection
- 根据图像线索动态加权多坡度特征，自适应融合生成统一高度图。
- 在OpenLane上实现64.3%的F-score，MAE和RMSE均优于现有方法。
- 适合需要高精度道路三维信息的自动驾驶场景，如路径规划与感知系统。
本文提出SC-Lane，一种面向3D车道线检测的坡度感知且时间一致的高度图估计框架。不同于依赖固定坡度锚点的以往方法，SC-Lane通过自适应机制融合多坡度高度特征，增强对复杂道路几何的鲁棒性。为此，我们设计了坡度感知自适应特征模块（Slope-Aware Adaptive Feature），基于图像线索动态预测权重，将多坡度表征融合为统一高度图。同时引入高度一致性模块（Height Consistency Module），确保连续帧间高度估计的稳定性与准确性，这对真实驾驶场景至关重要。为评估性能，我们采用三项标准指标：平均绝对误差（MAE）、均方根误差（RMSE）及阈值精度，这些指标虽广泛用于表面与深度估计，但在道路高度评估中仍较少使用。基于先前工作[20]提出的激光雷达生成高度图数据集，我们在该基准下进行评测，建立未来比较的严格标准。在OpenLane基准上的大量实验表明，SC-Lane显著提升高度估计与3D车道线检测性能，达到64.3%的F-score，领先于现有方法。
原文摘要 · Abstract (English)
In this paper, we introduce SC-Lane, a novel slope-aware and temporally consistent heightmap estimation framework for 3D lane detection. Unlike previous approaches that rely on fixed slope anchors, SC-Lane adaptively determines the fusion of slope-specific height features, improving robustness to diverse road geometries. To achieve this, we propose a Slope-Aware Adaptive Feature module that dynamically predicts the appropriate weights from image cues for integrating multi-slope representations into a unified heightmap. Additionally, a Height Consistency Module enforces temporal coherence, ensuring stable and accurate height estimation across consecutive frames, which is crucial for real-world driving scenarios. To evaluate the effectiveness of SC-Lane, we employ three standardized metrics-Mean Absolute Error(MAE), Root Mean Squared Error (RMSE), and threshold-based accuracy-which, although common in surface and depth estimation, have been underutilized for road height assessment. Using the LiDAR-derived heightmap dataset introduced in prior work [20], we benchmark our method under these metrics, thereby establishing a rigorous standard for future comparisons. Extensive experiments on the OpenLane benchmark demonstrate that SC-Lane significantly improves both height estimation and 3D lane detection, achieving state-of-the-art performance with an F-score of 64.3%, outperforming existing methods by a notable margin. For detailed results and a demonstration video, please refer to our project page:https://parkchaesong.github.io/sclane/
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。