A language-driven Mamba framework for low-dose CT denoising uses a frozen vision-language model to provide semantic supervision, achieving marginal but consistent quantitative gains over previous methods.
LIT-Former: Linking in-plane and through-plane transformers for simultaneous CT image denoising and deblurring,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
LangMamba: A Language-driven Mamba Framework for Low-dose CT Denoising with Vision-language Models
A language-driven Mamba framework for low-dose CT denoising uses a frozen vision-language model to provide semantic supervision, achieving marginal but consistent quantitative gains over previous methods.