A conditional diffusion model trained on hybrid noise-matched simulation and real segmented bone data improves CT spatial resolution without the noise amplification seen in simulation-only training.
Title resolution pending
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
-
Noise Controlled CT Super-Resolution with Conditional Diffusion Model
A conditional diffusion model trained on hybrid noise-matched simulation and real segmented bone data improves CT spatial resolution without the noise amplification seen in simulation-only training.