ADM uses interdependent score-based diffusion models and iterative Langevin sampling to achieve state-of-the-art alignment of SFI-UWFI retinal image pairs, with reported mAUC gains of 5.2 and 0.4 points over prior methods.
Title resolution pending
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
-
Active Diffusion Matching: Score-based Iterative Alignment of Cross-Modal Retinal Images
ADM uses interdependent score-based diffusion models and iterative Langevin sampling to achieve state-of-the-art alignment of SFI-UWFI retinal image pairs, with reported mAUC gains of 5.2 and 0.4 points over prior methods.