TPGDiff: Hierarchical Triple-Prior Guided Diffusion for Image Restoration

ArXi:2601.20306v2 Announce Type: replace All-in-one image restoration aims to address diverse degradation types using a single unified model. Existing methods typically rely on degradation priors to guide restoration, yet often struggle to reconstruct content in severely degraded regions. Although recent works leverage semantic information to facilitate content generation, integrating it into the shallow layers of diffusion models often disrupts spatial structures (\emph{e.g.}, blurring artifacts.