Marius Cordts


Cityscapes 3D is an extension of the original Cityscapes with 3D bounding box annotations for all types of vehicles as well as a benchmark for the 3D detection task. For more details please refer to our paper, presented at the CVPR 2020 Workshop on Scalability in Autonomous Driving. Today, we […]

Cityscapes 3D Benchmark Online


Cityscapes 3D is an extension of the original Cityscapes with 3D bounding box annotations for all types of vehicles as well as a benchmark for the 3D detection task. For more details please refer to our paper, presented at the CVPR 2020 Workshop on Scalability in Autonomous Driving. Today, we […]

Cityscapes 3D Dataset Released


Cityscapes 3D is an extension of the original Cityscapes with 3D bounding box annotations for all types of vehicles as well as a benchmark for the 3D detection task. For more details please refer to our paper, presented at the CVPR 2020 Workshop on Scalability in Autonomous Driving. Both, dataset […]

Coming Soon: Cityscapes 3D



The Cityscapes dataset is again part of the Robust Vision Challenge. The goal of this challenge is to foster the development of vision systems that are robust and consequently perform well on a variety of datasets with different characteristics. Towards this goal, performance is measured across a number of challenging benchmarks with different […]

Robust Vision Challenge 2020


The Cityscapes benchmark suite now includes panoptic segmentation [1], which combines pixel- and instance-level semantic segmentation. Our toolbox offers ground truth conversion and evaluation scripts. Our evaluation server and benchmark tables have been updated to support the new panoptic challenge. We thank Alexander Kirillov for helping with the implementation. [1] […]

Panoptic Segmentation