TY  - STD
AU  - Jose Luis Gomez
AU  - Manuel Silva
AU  - Antonio Seoane
AU  - Agnes Borras
AU  - Mario Noriega
AU  - German Ros
AU  - Jose Antonio Iglesias
AU  - Antonio Lopez
PY  - 2023//
TI  - All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes
N2  - 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).
UR  - https://arxiv.org/abs/2312.12176
L1  - http://refbase.cvc.uab.es/files/GSS2023.pdf
N1  - ADAS
ID  - Jose Luis Gomez2023
ER  -