Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision-10

3D Lane Detection

3260 papers • 126 benchmarks • 313 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 )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in 3d-lane-detection-10

Trend

Dataset

Best Model

Actions

OpenLane

OpenLane

Apollo Synthetic 3D Lane

Apollo Synthetic 3D Lane

OpenLane-V2 val

Libraries

i

Use these libraries to find 3d-lane-detection-10 models and implementations

Datasets

OpenLane

ONCE-3DLanes

OpenLane-V2 val

OpenLane-V2 val

OpenLane-V2 test

OpenLane-V2 test

Subtasks

No subtasks available.

Most implemented papers

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

Yang Li, Conghui He, Zehan Zheng, Junchi Yan, Li Chen, Chonghao Sima, Jiajie Xu, Xiangwei Geng, Hongyang Li, Jianping Shi, Yu Qiao•Sun Mar 20 2022

It is shown that PersFormer significantly outperforms competitive baselines in the 3D lane detection task on the authors' new OpenLane dataset as well as Apollo 3D Lane Synthetic dataset, and is also on par with state-of-the-art algorithms in the 2D task on OpenL Lane.

233

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

OpenLane-V2 val

OpenLane-V2 test

OpenLane-V2 test

0

ONCE-3DLanes: Building Monocular 3D Lane Detection

Yanwei Fu, Jianhua Han, Fan Yan, Ming-Jun Nie, Xinyue Cai, Han Xu, Zhengxin Yang, Chao Ye, M. B. Mi, Li Zhang•Fri Apr 29 2022

This work presents ONCE-3DLanes, a real-world autonomous driving dataset with lane layout annotation in 3D space, and presents an extrinsic-free, anchorfree method, called SALAD, regressing the 3D coordinates of lanes in image view without converting the feature map into the bird's-eye view (BEV).

87 0

VectorMapNet: End-to-end Vectorized HD Map Learning

Hang Zhao, Yue Wang, Yicheng Liu, Yilun Wang•Thu Jun 16 2022

This work introduces an end-to-end vectorized HD map learning pipeline, termed VectorMapNet, which takes onboard sensor observations and predicts a sparse set of polylines in the bird's-eye view and can explicitly model the spatial relation between map elements and generate vectorized maps that are friendly to downstream autonomous driving tasks.

298 0

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

Tomer Pe'er, Dan Levi, Noa Garnett, Rafi Cohen, Roee Lahav•Sun Nov 25 2018

This work marks a first attempt to address this task with on-board sensing without assuming a known constant lane width or relying on pre-mapped environments, and applies two new concepts: intra-network inverse-perspective mapping (IPM) and anchor-based lane representation.

224 0

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

Yuliang Guo, Guang Chen, Peitao Zhao, Weide Zhang, Jinghao Miao, Jingao Wang, T. Choe•Mon Mar 23 2020

This work introduces a new geometry-guided lane anchor representation in a new coordinate frame and applies a specific geometric transformation to directly calculate real 3D lane points from the network output and presents a scalable two-stage framework that decouples the learning of image segmentation subnetwork and geometry encoding subnetwork.

139 0

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

Ruijin Liu, Zejian Yuan, Tie Liu, Zhiliang Xiong, Dapeng Chen•Thu Dec 30 2021

This work proposes to predict 3D lanes by estimating camera pose from a single image with a two-stage framework and demonstrates that, without ground truth camera pose, this method outperforms the state-of-the-art perfect-camera-pose-based methods and has the fewest parameters and computations.

60 0

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

X. Zhang, Junjie Yan, Jian Sun, Yingfei Liu, Fan Jia, Shuailin Li, Qi Gao, Tiancai Wang•Wed Jun 01 2022

PETRv2, a unified framework for 3D perception from multi-view images, is proposed and the 3D position embedding in PETR is extended for temporal modeling, which achieves the temporal alignment on object position of different frames.

474 0

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

Tianheng Cheng, Xinggang Wang, Wenyu Liu, Chang Huang, Bencheng Liao, Shaoyu Chen, Qian Zhang•Mon Aug 29 2022

A unified permutation-equivalent modeling approach is proposed, i.e., modeling map element as a point set with a group of equivalent permutations, which accurately describes the shape of map element and stabilizes the learning process.

342 0

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

Jianyong Ai, Wenbo Ding, Jiu-Yang Zhao, Jiachen Zhong•Thu Sep 22 2022

In anchor representation, a double-layer anchor with non-maximum suppression (NMS) method is proposed, which enables the anchor-based method to predict two lane lines that are close and is the first try of 3D lane detection under weakly supervised setting.

14 0

Adding a benchmark result helps the community track progress.

3D Lane Detection | State-of-the-Art