3D Lane Detection

21 papers with code • 4 benchmarks • 4 datasets

The goal of 3D Lane Detection is to perceive lanes that provide guidance for autonomous vehicles. A lane can be represented as a visible laneline or a conceptual centerline. Furthermore, a lane obtains extra attributes from the understanding of the surrounding environment.

( Image credit: OpenLane-V2 )

Most implemented papers

VectorMapNet: End-to-end Vectorized HD Map Learning

Mrmoore98/VectorMapNet_code 17 Jun 2022

To the best of our knowledge, VectorMapNet is the first work designed towards end-to-end vectorized map learning from onboard observations.

PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark

OpenDriveLab/PersFormer_3DLane 21 Mar 2022

Methods for 3D lane detection have been recently proposed to address the issue of inaccurate lane layouts in many autonomous driving scenarios (uphill/downhill, bump, etc.).

ONCE-3DLanes: Building Monocular 3D Lane Detection

once-3dlanes/once_3dlanes_benchmark CVPR 2022

We present ONCE-3DLanes, a real-world autonomous driving dataset with lane layout annotation in 3D space.

3D-LaneNet: End-to-End 3D Multiple Lane Detection

yuliangguo/Pytorch_Generalized_3D_Lane_Detection ICCV 2019

We introduce a network that directly predicts the 3D layout of lanes in a road scene from a single image.

Gen-LaneNet: A Generalized and Scalable Approach for 3D Lane Detection

yuliangguo/Pytorch_Generalized_3D_Lane_Detection ECCV 2020

The method, inspired by the latest state-of-the-art 3D-LaneNet, is a unified framework solving image encoding, spatial transform of features and 3D lane prediction in a single network.

Learning to Predict 3D Lane Shape and Camera Pose from a Single Image via Geometry Constraints

liuruijin17/clgo 31 Dec 2021

In this task, the correct camera pose is the key to generating accurate lanes, which can transform an image from perspective-view to the top-view.

PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images

megvii-research/petr ICCV 2023

More specifically, we extend the 3D position embedding (3D PE) in PETR for temporal modeling.

MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction

hustvl/maptr 30 Aug 2022

High-definition (HD) map provides abundant and precise environmental information of the driving scene, serving as a fundamental and indispensable component for planning in autonomous driving system.

WS-3D-Lane: Weakly Supervised 3D Lane Detection With 2D Lane Labels

SAIC-Vision/WS-3D-Lane 23 Sep 2022

To the best of our knowledge, WS-3D-Lane is the first try of 3D lane detection under weakly supervised setting.