M$^2$-3DLaneNet: Exploring Multi-Modal 3D Lane Detection

TL;DR

This paper introduces M$^2$-3DLaneNet, a multi-modal approach combining LiDAR and image data to improve 3D lane detection accuracy, addressing limitations of previous image-only methods.

Contribution

It proposes a novel multi-modal framework that lifts 2D features into 3D using LiDAR data and fuses features across modalities for enhanced lane detection.

Findings

Effective on large-scale OpenLane dataset

Performs well at ranges up to 100 meters

Outperforms image-only methods

Abstract

Estimating accurate lane lines in 3D space remains challenging due to their sparse and slim nature. Previous works mainly focused on using images for 3D lane detection, leading to inherent projection error and loss of geometry information. To address these issues, we explore the potential of leveraging LiDAR for 3D lane detection, either as a standalone method or in combination with existing monocular approaches. In this paper, we propose M$^2$-3DLaneNet to integrate complementary information from multiple sensors. Specifically, M$^2$-3DLaneNet lifts 2D features into 3D space by incorporating geometry information from LiDAR data through depth completion. Subsequently, the lifted 2D features are further enhanced with LiDAR features through cross-modality BEV fusion. Extensive experiments on the large-scale OpenLane dataset demonstrate the effectiveness of M$^2$-3DLaneNet, regardless of the range (75m or 100m).