All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes
Jose L. G\'omez, Manuel Silva, Antonio Seoane, Agn\`es Borr\'as, Mario, Noriega, Germ\'an Ros, Jose A. Iglesias-Guitian, Antonio M. L\'opez

TL;DR
UrbanSyn is a high-quality synthetic urban driving dataset that enhances domain adaptation and improves semantic segmentation benchmarks on real-world datasets.
Contribution
We introduce UrbanSyn, a photorealistic synthetic dataset that complements existing datasets and advances unsupervised domain adaptation for urban scene understanding.
Findings
UrbanSyn improves semantic segmentation accuracy on real-world datasets.
UrbanSyn establishes new benchmark results in domain adaptation.
UrbanSyn is publicly accessible for research use.
Abstract
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 (www.urbansyn.org).
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · Domain Adaptation and Few-Shot Learning · Multimodal Machine Learning Applications
