A dual-domain diffusion model trained only on normal-dose CT data generalizes to unseen low-dose levels by matching Poisson noise in projections and refining images with double guidance.
, author Leng, S
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Noise-Inspired Diffusion Model for Generalizable Low-Dose CT Reconstruction
A dual-domain diffusion model trained only on normal-dose CT data generalizes to unseen low-dose levels by matching Poisson noise in projections and refining images with double guidance.