GTA5 (Grand Theft Auto 5)

Introduced by Richter et al. in Playing for Data: Ground Truth from Computer Games

The GTA5 dataset contains 24966 synthetic images with pixel level semantic annotation. The images have been rendered using the open-world video game Grand Theft Auto 5 and are all from the car perspective in the streets of American-style virtual cities. There are 19 semantic classes which are compatible with the ones of Cityscapes dataset.

Source: Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Synthetic-to-Real Translation	GTAV-to-Cityscapes Labels	DCF
Domain Adaptation	GTA5 to Cityscapes	DCF
Image-to-Image Translation	GTAV-to-Cityscapes Labels	MIC
Unsupervised Domain Adaptation	GTAV-to-Cityscapes Labels	MIC
Semantic Segmentation	GTAV-to-Cityscapes Labels	MIC
Domain Adaptation	GTA5+Synscapes to Cityscapes	MSCL
One-shot Unsupervised Domain Adaptation	GTA5 to Cityscapes	HRDA+DATUM