Content

Pix2Pix's Cityscapes dataset consists of 3475 dashcam images and their corresponding ground truth scene segmentatations split into train and test subsets.

Acknowledgements

This dataset was obtained from UC Berkeley's official directory of Pix2Pix Datasets. For more details on the dataset refer the related Pix2Pix publication. Work based on the dataset should cite:

@inproceedings{isola2017image,   title={Image-to-image translation with conditional adversarial networks},   author={Isola, Phillip and Zhu, Jun-Yan and Zhou, Tinghui and Efros, Alexei A},   booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},   pages={1125--1134},   year={2017} }