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 extended our benchmark and evaluation server to include the 3D vehicle detection task. In order to train and evaluate your method, checkout our toolbox on Github, which can be installed using pip, i.e.python -m pip install cityscapesscripts[gui]. In order to visualize the 3D Boxes, run csViewer and select the CS3D ground truth. The toolbox also includes our evaluation code, run csEvalObjectDetection3d -h for details. First, evaluate your method on the validation set. Then, submit your test set results on our evaluation server.

The tool csViewer can be used to visualize the 3D bounding box annotations.