Radar Doppler velocities, clustered under rigidity assumptions, can be propagated to LiDAR as pseudo scene flow labels, outperforming self-supervised baselines on TruckScenes and improving label efficiency.
Towards long-range 3d object detection for autonomous vehicles,
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
-
DoGFlow: Self-Supervised LiDAR Scene Flow via Cross-Modal Doppler Guidance
Radar Doppler velocities, clustered under rigidity assumptions, can be propagated to LiDAR as pseudo scene flow labels, outperforming self-supervised baselines on TruckScenes and improving label efficiency.