A frozen DINOv2 vision foundation model, adapted with lightweight MultiConv adapters on a three-channel range image view of LiDAR scans, achieves state-of-the-art LiDAR place recognition and generalizes across sensors.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ImLPR: Image-based LiDAR Place Recognition using Vision Foundation Models
A frozen DINOv2 vision foundation model, adapted with lightweight MultiConv adapters on a three-channel range image view of LiDAR scans, achieves state-of-the-art LiDAR place recognition and generalizes across sensors.