KITTI dataset

doi:doi:10.57702/tn28izko

KITTI dataset

The dataset used in the paper is the KITTI dataset, which is a benchmark for monocular depth estimation. The dataset consists of a large collection of images and corresponding depth maps, which are used to train and evaluate depth estimation models.

BibTex:

@dataset{Andreas_Geiger_and_Philip_Lenz_and_Christoph_Stiller_and_Raquel_Urtasun_2024,
    abstract = {The dataset used in the paper is the KITTI dataset, which is a benchmark for monocular depth estimation. The dataset consists of a large collection of images and corresponding depth maps, which are used to train and evaluate depth estimation models.},
    author = {Andreas Geiger and Philip Lenz and Christoph Stiller and Raquel Urtasun},
    doi = {10.57702/tn28izko},
    institution = {No Organization},
    keyword = {'2D Object Detection', '2D object detection', '3D LiDAR', '3D Object Detection', '3D Point Cloud', '3D Point Clouds', '3D Vision', '3D localization', '3D object detection', '3D scene understanding', 'Autonomous Driving', 'Autonomous Vehicles', 'Autonomous vehicles', 'Benchmark', 'Camera', 'Computer Vision', 'Depth Completion', 'Depth Maps', 'Depth estimation', 'Highway', 'Image Processing', 'Image Sequences', 'Image sequences', 'Images', 'KITTI', 'KITTI dataset', 'LIDAR sensor', 'LiDAR', 'LiDAR scans', 'Motion field', 'Object Detection', 'Object Recognition', 'Object detection', 'Odometry', 'Optical Flow', 'Optical flow', 'Point Clouds', 'RGB', 'RGB images', 'Rural', 'Scene Understanding', 'Semantic Segmentation', 'Stereo Images', 'Stereo Matching', 'Transportation Scenarios', 'Urban', 'Urban Environments', 'Visual Odometry', 'annotations', 'autonomous driving', 'autonomous vehicles', 'camera', 'car detection', 'color images', 'computer vision', 'depth estimation', 'ego-motion estimation', 'image dataset', 'images', 'monocular', 'monocular 3D object detection', 'monocular camera', 'monocular depth estimation', 'monocular visual odometry', 'multi-object tracking', 'object detection', 'object tracking', 'pedestrian detection', 'point cloud', 'scenes', 'self-driving', 'semantic segmentation', 'single image', 'single image depth estimation', 'sparse depth maps', 'stereo', 'stereo vision', 'structure from motion', 'vehicles', 'videos', 'visual SLAM', 'visual odometry'},
    month = {nov},
    publisher = {TIB},
    title = {KITTI dataset},
    url = {https://service.tib.eu/ldmservice/dataset/kitti-dataset},
    year = {2024}
}