Depth3DLane: Fusing Monocular 3D Lane Detection with Self-Supervised Monocular Depth Estimation

TL;DR

Depth3DLane introduces a dual-pathway framework that combines self-supervised monocular depth estimation with multi-view lane detection, enabling accurate 3D lane detection without expensive sensors or ground-truth depth data, and adaptable to uncalibrated scenarios.

Contribution

It presents a novel framework integrating self-supervised depth estimation with 3D lane detection, removing the need for ground-truth depth and camera calibration, and extending applicability to crowdsourced mapping.

Findings

Achieves competitive results on OpenLane benchmark.

Effectively predicts camera parameters per frame.

Operates without ground-truth depth or calibration data.

Abstract

Monocular 3D lane detection is essential for autonomous driving, but challenging due to the inherent lack of explicit spatial information. Multi-modal approaches rely on expensive depth sensors, while methods incorporating fully-supervised depth networks rely on ground-truth depth data that is impractical to collect at scale. Additionally, existing methods assume that camera parameters are available, limiting their applicability in scenarios like crowdsourced high-definition (HD) lane mapping. To address these limitations, we propose Depth3DLane, a novel dual-pathway framework that integrates self-supervised monocular depth estimation to provide explicit structural information, without the need for expensive sensors or additional ground-truth depth data. Leveraging a self-supervised depth network to obtain a point cloud representation of the scene, our bird's-eye view pathway extracts explicit spatial information, while our front view pathway simultaneously extracts rich semantic information. Depth3DLane then uses 3D lane anchors to sample features from both pathways and infer accurate 3D lane geometry. Furthermore, we extend the framework to predict camera parameters on a per-frame basis and introduce a theoretically motivated fitting procedure to enhance stability on a per-segment basis. Extensive experiments demonstrate that Depth3DLane achieves competitive performance on the OpenLane benchmark dataset. Furthermore, experimental results show that using learned parameters instead of ground-truth parameters allows Depth3DLane to be applied in scenarios where camera calibration is infeasible, unlike previous methods.