Virtual KITTI 2

Creative Commons Attribution-NonCommercial-ShareAlike 3.0Introduced 2020-01-29

Virtual KITTI 2 is an updated version of the well-known Virtual KITTI dataset which consists of 5 sequence clones from the KITTI tracking benchmark. In addition, the dataset provides different variants of these sequences such as modified weather conditions (e.g. fog, rain) or modified camera configurations (e.g. rotated by 15◦). For each sequence we provide multiple sets of images containing RGB, depth, class segmentation, instance segmentation, flow, and scene flow data. Camera parameters and poses as well as vehicle locations are available as well. In order to showcase some of the dataset’s capabilities, we ran multiple relevant experiments using state-of-the-art algorithms from the field of autonomous driving. The dataset is available for download at https://europe.naverlabs.com/Research/Computer-Vision/Proxy-Virtual-Worlds.

Benchmarks

16k/mAP@0.3 16k/mAP@0.5 2D Classification/mAP@0.3 2D Classification/mAP@0.5 2D Object Detection/mAP@0.3 2D Object Detection/mAP@0.5 3D/mAP@0.3 3D/mAP@0.5 3D/Delta < 1.25 3D/RMSE 3D/absolute relative error 3D Object Detection/mAP@0.3 3D Object Detection/mAP@0.5 Depth Estimation/Delta < 1.25 Depth Estimation/RMSE Depth Estimation/absolute relative error Object Detection/mAP@0.3 Object Detection/mAP@0.5