# Synthetic-to-Real Domain Adaptation for Lane Detection

arXiv: https://arxiv.org/abs/2007.04023 · HTML: https://mlsanity.com/paper/2007.04023/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2020.

## Built on by (most cited first, 11 of 11)

- [PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark](https://mlsanity.com/paper/2203.11089/) (2022)
- [ONCE-3DLanes: Building Monocular 3D Lane Detection](https://mlsanity.com/paper/2205.00301/) (2022)
- [Sim-to-Real Domain Adaptation for Lane Detection and Classification in Autonomous Driving](https://mlsanity.com/paper/2202.07133/) (2022)
- [CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World Domains](https://mlsanity.com/paper/2206.08083/) (2022)
- [LaneCorrect: Self-supervised Lane Detection](https://mlsanity.com/paper/2404.14671/) (2024)
- [UnrealROX+: An Improved Tool for Acquiring Synthetic Data from Virtual 3D Environments](https://mlsanity.com/paper/2104.11776/) (2021)
- [Domain Adaptation for Rare Classes Augmented with Synthetic Samples](https://mlsanity.com/paper/2110.12216/) (2021)
- [UDA4Inst: Unsupervised Domain Adaptation for Instance Segmentation](https://mlsanity.com/paper/2405.09682/) (2024)
- [Unsupervised Domain Adaptive Lane Detection via Contextual Contrast and Aggregation](https://mlsanity.com/paper/2407.13328/) (2024)
- [Datasets for Lane Detection in Autonomous Driving: A Comprehensive Review](https://mlsanity.com/paper/2504.08540/) (2025)
- [A System-driven Automatic Ground Truth Generation Method for DL Inner-City Driving Corridor Detectors](https://mlsanity.com/paper/2207.11234/) (2022)

## Abstract (arXiv)

Accurate lane detection, a crucial enabler for autonomous driving, currently relies on obtaining a large and diverse labeled training dataset. In this work, we explore learning from abundant, randomly generated synthetic data, together with unlabeled or partially labeled target domain data, instead. Randomly generated synthetic data has the advantage of controlled variability in the lane geometry and lighting, but it is limited in terms of photo-realism. This poses the challenge of adapting models learned on the unrealistic synthetic domain to real images. To this end we develop a novel autoencoder-based approach that uses synthetic labels unaligned with particular images for adapting to target domain data. In addition, we explore existing domain adaptation approaches, such as image translation and self-supervision, and adjust them to the lane detection task. We test all approaches in the unsupervised domain adaptation setting in which no target domain labels are available and in the semi-supervised setting in which a small portion of the target images are labeled. In extensive experiments using three different datasets, we demonstrate the possibility to save costly target domain labeling efforts. For example, using our proposed autoencoder approach on the llamas and tuSimple lane datasets, we can almost recover the fully supervised accuracy with only 10% of the labeled data. In addition, our autoencoder approach outperforms all other methods in the semi-supervised domain adaptation scenario.