Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving
This addresses the problem of safe navigation for autonomous vehicles by providing a dataset to test anomaly detection, though it is incremental as it builds on existing 2D research.
The paper tackles the lack of high-quality multimodal datasets for anomaly segmentation in 3D autonomous driving by introducing the first publicly available dataset with dense 3D semantic labeling, LiDAR, camera data, and sequential information, and it evaluates baseline models to highlight challenges in this area.
To operate safely, autonomous vehicles (AVs) need to detect and handle unexpected objects or anomalies on the road. While significant research exists for anomaly detection and segmentation in 2D, research progress in 3D is underexplored. Existing datasets lack high-quality multimodal data that are typically found in AVs. This paper presents a novel dataset for anomaly segmentation in driving scenarios. To the best of our knowledge, it is the first publicly available dataset focused on road anomaly segmentation with dense 3D semantic labeling, incorporating both LiDAR and camera data, as well as sequential information to enable anomaly detection across various ranges. This capability is critical for the safe navigation of autonomous vehicles. We adapted and evaluated several baseline models for 3D segmentation, highlighting the challenges of 3D anomaly detection in driving environments. Our dataset and evaluation code will be openly available, facilitating the testing and performance comparison of different approaches.