Welcome to the KITTI Vision Benchmark Suite! We take advantage of our autonomous driving platform Annieway to develop novel challenging real-world computer vision benchmarks. Our tasks of interest …

Jack Borer has written a motion compensation library for the Lidar scans in the KITTI dataset. Note: We were not able to annotate all sequences and only provide those tracklet annotations that passed the …

Important Policy Update: As more and more non-published work and re-implementations of existing work is submitted to KITTI, we have established a new policy: from now on, only submissions with …

Virtual KITTI Dataset: Virtual KITTI contains 50 high-resolution monocular videos (21,260 frames) generated from five different virtual worlds in urban settings under different imaging and weather …

This setup is similar to the one used in KITTI, except that we gain a full 360° field of view due to the additional fisheye cameras and the pushbroom laser scanner while KITTI only provides perspective …

This page provides additional information about the recording platform and sensor setup we have used to record this dataset. Our recording platform is a Volkswagen Passat B6, which has been modified …

In addition to the raw data, our KITTI website hosts evaluation benchmarks for several computer vision and robotic tasks such as stereo, optical flow, visual odometry, SLAM, 3D object detection and 3D …

Here we collect a number of resources where people have annotated KITTI images with semantic labels. Please let me know if you have annotated some part or are aware of any further labels which …

This is our 2D object detection and orientation estimation benchmark; it consists of 7481 training images and 7518 testing images. The benchmark uses 2D bounding box overlap to compute precision-recall …

It is based on the KITTI Tracking Evaluation 2012 and extends the annotations to the Multi-Object and Segmentation (MOTS) task. To this end, we added dense pixelwise segmentation labels for every …