STU is the first public 3D LiDAR dataset to provide dense semantic and instance labels for road anomalies, and baseline tests show current methods detect very few of them.
Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving
STU is the first public 3D LiDAR dataset to provide dense semantic and instance labels for road anomalies, and baseline tests show current methods detect very few of them.