4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving

TL;DR

The paper introduces 4Seasons, a comprehensive dataset for autonomous driving that captures diverse weather, lighting, and seasonal conditions, supporting research in visual odometry, place recognition, and re-localization.

Contribution

It provides a large, multi-environment dataset with high-precision reference poses under varied conditions, enabling robust multi-weather SLAM research.

Findings

Over 350 km of recordings across nine environments.

High-accuracy reference poses from visual-inertial odometry and RTK-GNSS.

Diverse conditions including day/night, weather, and seasons.

Abstract

We present a novel dataset covering seasonal and challenging perceptual conditions for autonomous driving. Among others, it enables research on visual odometry, global place recognition, and map-based re-localization tracking. The data was collected in different scenarios and under a wide variety of weather conditions and illuminations, including day and night. This resulted in more than 350 km of recordings in nine different environments ranging from multi-level parking garage over urban (including tunnels) to countryside and highway. We provide globally consistent reference poses with up-to centimeter accuracy obtained from the fusion of direct stereo visual-inertial odometry with RTK-GNSS. The full dataset is available at https://go.vision.in.tum.de/4seasons.