A 4D radar-only occupancy model trained with LiDAR pseudo-labels and height-map supervision approaches LiDAR-quality occupancy and runs at about 30 Hz.
Get it for free: Radar segmentation without expert labels and its application in odometry and localization,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
4D-ROLLS: 4D Radar Occupancy Learning via LiDAR Supervision
A 4D radar-only occupancy model trained with LiDAR pseudo-labels and height-map supervision approaches LiDAR-quality occupancy and runs at about 30 Hz.