PANSv2, a combination of foundation-model depth and landmark cues with centerline constraints and failure re-initialization, reports SR-5 of 46.5% on filtered frames, 18.1 points above the previous best on a private dataset.
Interna- tional Journal of Computer Assisted Radiology and Surgery19(4), 713–721 (2024)
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
-
Harnessing Foundation Models for Robust and Generalizable 6-DOF Bronchoscopy Localization
PANSv2, a combination of foundation-model depth and landmark cues with centerline constraints and failure re-initialization, reports SR-5 of 46.5% on filtered frames, 18.1 points above the previous best on a private dataset.