By fine-tuning Stable Diffusion on a curated aesthetic dataset with learned quality-specific prompt tokens, RAP-SR improves the perceptual quality of several diffusion-based super-resolution methods, as measured by no-reference metrics.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RAP-SR: RestorAtion Prior Enhancement in Diffusion Models for Realistic Image Super-Resolution
By fine-tuning Stable Diffusion on a curated aesthetic dataset with learned quality-specific prompt tokens, RAP-SR improves the perceptual quality of several diffusion-based super-resolution methods, as measured by no-reference metrics.