Adaptive geodesic conformal prediction with a cross-participant DINOv2-Bridge difficulty estimator closes the 30-point conditional coverage gap for the hardest 25% of egocentric pose frames while preserving 90% overall coverage.
DROID-SLAM: Deep visual SLAM for monocular, stereo, and RGB-D cameras
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
-
Adaptive Geodesic Conformal Prediction for Egocentric Camera Pose Estimation
Adaptive geodesic conformal prediction with a cross-participant DINOv2-Bridge difficulty estimator closes the 30-point conditional coverage gap for the hardest 25% of egocentric pose frames while preserving 90% overall coverage.