Virtual KITTI 2

Abstract

This paper introduces 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 degrees). 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.

Cited by in corpus (9)

• Tree Detection and Diameter Estimation Based on Deep Learning
• Quantifying the LiDAR Sim-to-Real Domain Shift: A Detailed Investigation Using Object Detectors and Analyzing Point Clouds at Target-Level
• MOPT: Multi-Object Panoptic Tracking
• Object Detector Differences when using Synthetic and Real Training Data
• Simultaneous Localization and Mapping Related Datasets: A Comprehensive Survey
• Towards Real-Time Monocular Depth Estimation for Robotics: A Survey
• Information-Theoretic Odometry Learning
• Monocular Depth Prediction through Continuous 3D Loss
• Do End-to-end Stereo Algorithms Under-utilize Information?