Frozen DINOv2 features and Metric3Dv2 depth improve Lift-Splat-Shoot BEV segmentation by up to 8.9 IoU and a Metric3Dv2 PseudoLiDAR cloud adds about 3 IoU to Simple-BEV camera-only.
Title resolution pending
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
-
Revisiting Birds Eye View Perception Models with Frozen Foundation Models: DINOv2 and Metric3Dv2
Frozen DINOv2 features and Metric3Dv2 depth improve Lift-Splat-Shoot BEV segmentation by up to 8.9 IoU and a Metric3Dv2 PseudoLiDAR cloud adds about 3 IoU to Simple-BEV camera-only.