SC-Lane: Slope-aware and Consistent Road Height Estimation Framework for 3D Lane Detection

TL;DR

SC-Lane is a novel framework for 3D lane detection that adaptively estimates road height by considering slope variations and enforces temporal consistency, leading to improved accuracy and robustness in diverse driving scenarios.

Contribution

The paper introduces a slope-aware adaptive feature module and a height consistency module, advancing 3D lane detection with dynamic slope integration and temporal stability.

Findings

Achieves state-of-the-art F-score of 64.3% on OpenLane benchmark.

Significantly outperforms existing methods in height estimation accuracy.

Demonstrates robustness across diverse road geometries.

Abstract

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/