UniRestore adapts a Stable Diffusion restoration model to simultaneously improve perceptual quality, classification accuracy, and segmentation mIoU by restoring encoder features and using task-specific prompts.
All snow re- moved: Single image desnowing algorithm using hierarchi- cal dual-tree complex wavelet representation and contradict channel loss
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
background 1representative citing papers
citing papers explorer
-
UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior
UniRestore adapts a Stable Diffusion restoration model to simultaneously improve perceptual quality, classification accuracy, and segmentation mIoU by restoring encoder features and using task-specific prompts.