KITTI-360 - A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D

Explore the KITTI-360 dataset, a comprehensive resource for urban scene understanding in 2D and 3D, through this 23-minute conference talk by Andreas Geiger. Learn about the dataset's rich input modalities, extensive semantic instance annotations, and accurate localization designed to facilitate research at the intersection of computer vision, graphics, and robotics. Discover the innovative annotation tools and models used to create over 150,000 semantically and instance-annotated images and 1 billion annotated 3D points. Gain insights into the benchmarks and baselines established for various mobile perception tasks, encompassing problems from multiple research areas. Understand how KITTI-360 aims to contribute to the development of fully autonomous self-driving systems by enabling progress at the convergence of computer vision, graphics, and robotics.

Intro
Combining Perception and Action
Combining Perception and Simulation
Towards Full Autonomy
Data Collection Data
The Curse of Dataset Annotation
3D to 2D Semantic and Instance Label Transfer
Data Annotation
Static Object Annotation
Semi-Automatic Dynamic Object Annotation
3D-to-2D Label Transfer
Qualitative Comparison to Baselines
Qualitative Results
Semantic Scene Understanding
Novel View Synthesis
Benchmarks
Semantic SLAM
Leaderboard
Resources