We introduce UrbanSyn, a photorealistic dataset acquired through semi-procedurally generated synthetic urban driving scenarios. Developed using high-quality geometry and materials, UrbanSyn provides pixel-level ground truth, including depth, semantic segmentation, and instance segmentation with object bounding boxes and occlusion degree. It complements GTAV and Synscapes datasets to form what we coin as the 'Three Musketeers'. We demonstrate the value of the Three Musketeers in unsupervised domain adaptation for image semantic segmentation. Results on real-world datasets, Cityscapes, Mapillary Vistas, and BDD100K, establish new benchmarks, largely attributed to UrbanSyn. We make UrbanSyn openly and freely accessible (this http URL).
View on arXiv@article{gómez2025_2312.12176,
title={ All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes },
author={ Jose L. Gómez and Manuel Silva and Antonio Seoane and Agnès Borrás and Mario Noriega and Germán Ros and Jose A. Iglesias-Guitian and Antonio M. López },
journal={arXiv preprint arXiv:2312.12176},
year={ 2025 }
}