# Reconstruct from BEV: A 3D Lane Detection Approach based on Geometry Structure Prior

arXiv: https://arxiv.org/abs/2206.10098 · HTML: https://mlsanity.com/paper/2206.10098/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 40 references that are in the map.
- First posted on arXiv 21 Jun 2022.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [Spatial As Deep: Spatial CNN for Traffic Scene Understanding](https://mlsanity.com/paper/1712.06080/) (2017)
- [Towards End-to-End Lane Detection: an Instance Segmentation Approach](https://mlsanity.com/paper/1802.05591/) (2018)
- [3D-LaneNet: End-to-End 3D Multiple Lane Detection](https://mlsanity.com/paper/1811.10203/) (2018)
- [Gen-LaneNet: A Generalized and Scalable Approach for 3D Lane Detection](https://mlsanity.com/paper/2003.10656/) (2020)
- [Monocular 3D Object Detection: An Extrinsic Parameter Free Approach](https://mlsanity.com/paper/2106.15796/) (2021)
- [DAGMapper: Learning to Map by Discovering Lane Topology](https://mlsanity.com/paper/2012.12377/) (2020)
- [Real time Detection of Lane Markers in Urban Streets](https://mlsanity.com/paper/1411.7113/) (2014)
- [3D-LaneNet+: Anchor Free Lane Detection using a Semi-Local Representation](https://mlsanity.com/paper/2011.01535/) (2020)
- [Deep Multi-Sensor Lane Detection](https://mlsanity.com/paper/1905.01555/) (2019)

## Built on by (most cited first, 2 of 2)

- [GLane3D : Detecting Lanes with Graph of 3D Keypoints](https://mlsanity.com/paper/2503.23882/) (2025)
- [Depth3DLane: Fusing Monocular 3D Lane Detection with Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2507.13857/) (2025)

## Abstract (arXiv)

In this paper, we propose an advanced approach in targeting the problem of monocular 3D lane detection by leveraging geometry structure underneath the process of 2D to 3D lane reconstruction. Inspired by previous methods, we first analyze the geometry heuristic between the 3D lane and its 2D representation on the ground and propose to impose explicit supervision based on the structure prior, which makes it achievable to build inter-lane and intra-lane relationships to facilitate the reconstruction of 3D lanes from local to global. Second, to reduce the structure loss in 2D lane representation, we directly extract BEV lane information from front view images, which tremendously eases the confusion of distant lane features in previous methods. Furthermore, we propose a novel task-specific data augmentation method by synthesizing new training data for both segmentation and reconstruction tasks in our pipeline, to counter the imbalanced data distribution of camera pose and ground slope to improve generalization on unseen data. Our work marks the first attempt to employ the geometry prior information into DNN-based 3D lane detection and makes it achievable for detecting lanes in an extra-long distance, doubling the original detection range. The proposed method can be smoothly adopted by other frameworks without extra costs. Experimental results show that our work outperforms state-of-the-art approaches by 3.8% F-Score on Apollo 3D synthetic dataset at real-time speed of 82 FPS without introducing extra parameters.