LEADER cuts position error by 24.1% on Oxford RobotCar and 73.9% on NCLT by combining a projection-based geometric encoder with a truncated relative reliability loss that down-weights unreliable points.
Feature- metric registration: A fast semi-supervised approach for ro- bust point cloud registration without correspondences
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LEADER: Learning Reliable Local-to-Global Correspondences for LiDAR Relocalization
LEADER cuts position error by 24.1% on Oxford RobotCar and 73.9% on NCLT by combining a projection-based geometric encoder with a truncated relative reliability loss that down-weights unreliable points.