Pre-trained diffusion models inherently support image restoration that can be unlocked by optimizing prompt embeddings at the text encoder output using a diffusion bridge formulation, achieving competitive results on models like WAN and FLUX without fine-tuning.
Uni- versal image restoration pre-training via degradation classi- fication
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5representative citing papers
The paper proposes the Degradation Frequency Curve (DFC) as an explicit spectral representation for quantifying degradations and develops a DFC-guided multi-scale restorer that achieves state-of-the-art performance on composite and real-world benchmarks.
DAME-Net decouples explicit per-factor degradation perception from conditioned reconstruction via a Mixture-of-Experts architecture, achieving better compositional UAV image restoration than unified methods on the new MDUR benchmark with 43 degradation configurations.
DVANet proposes a deep unfolding network combining degradation representation with DINOv3 visual priors for unified restoration under complex degradations.
TPGDiff introduces hierarchical triple-prior guidance in a diffusion network, placing degradation priors throughout, structural priors in shallow layers, and semantic priors in deep layers for improved all-in-one image restoration.
citing papers explorer
-
Your Pre-trained Diffusion Model Secretly Knows Restoration
Pre-trained diffusion models inherently support image restoration that can be unlocked by optimizing prompt embeddings at the text encoder output using a diffusion bridge formulation, achieving competitive results on models like WAN and FLUX without fine-tuning.
-
Degradation Frequency Curve: An Explicit Frequency-Quantified Representation for All-in-One Image Restoration
The paper proposes the Degradation Frequency Curve (DFC) as an explicit spectral representation for quantifying degradations and develops a DFC-guided multi-scale restorer that achieves state-of-the-art performance on composite and real-world benchmarks.
-
Compositional-Degradation UAV Image Restoration: Conditional Decoupled MoE Network and A Benchmark
DAME-Net decouples explicit per-factor degradation perception from conditioned reconstruction via a Mixture-of-Experts architecture, achieving better compositional UAV image restoration than unified methods on the new MDUR benchmark with 43 degradation configurations.
-
DVANet: Degradation-aware Visual-prior Alignment Network for Image Restoration
DVANet proposes a deep unfolding network combining degradation representation with DINOv3 visual priors for unified restoration under complex degradations.
-
TPGDiff: Hierarchical Triple-Prior Guided Diffusion for Image Restoration
TPGDiff introduces hierarchical triple-prior guidance in a diffusion network, placing degradation priors throughout, structural priors in shallow layers, and semantic priors in deep layers for improved all-in-one image restoration.