All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes

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).

arXiv commentThe UrbanSyn Dataset is available in http://urbansyn.org/

References in corpus (7)

• Deep Visual Domain Adaptation: A Survey
• Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches
• A Survey of End-to-End Driving: Architectures and Training Methods
• Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing
• Critically Examining the "Neural Hype": Weak Baselines and the Additivity of Effectiveness Gains from Neural Ranking Models
• DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation
• Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models