Degradation Frequency Curve: An Explicit Frequency-Quantified Representation for All-in-One Image Restoration
For the field of blind image restoration, this work provides a novel explicit representation of degradation that improves performance and generalization across diverse and unseen degradation types.
The paper introduces the Degradation Frequency Curve (DFC), a spectral representation that quantifies degradation responses in the frequency domain, enabling all-in-one image restoration. The proposed DFC-IR framework achieves state-of-the-art performance on standard, composite, unseen, and real-world degradation benchmarks, with improved generalization under complex degradation profiles.
A fundamental difficulty in all-in-one blind image restoration is that degradation is usually treated as an implicit factor hidden in degraded-to-clean mapping, rather than as an explicit object that can be measured and manipulated. This limitation becomes more pronounced under mixed, compound, or unseen degradation conditions, where degradation effects are hard to assign to predefined labels or task-specific parameters. We propose the Degradation Frequency Curve (DFC), a structured spectral representation that quantifies degradation responses by measuring band-wise residual-to-degraded energy ratios in the frequency domain. DFC converts visually entangled and hard-to-describe degradation effects into a measurable degradation coordinate space. Moreover, DFC can be adaptively decomposed into band-wise spectral tokens, allowing local degradation responses to be represented as reusable restoration priors. Based on this representation, we develop the DFC-guided Image Restorer (DFC-IR), a token-conditioned multi-scale framework that progressively estimates DFCs from intermediate restorations and uses the resulting spectral tokens to guide degradation-aware restoration in a coarse-to-fine manner. Extensive experiments on standard, composite, unseen, and real-world degradation benchmarks show that DFC provides an effective representation basis for all-in-one restoration, leading to state-of-the-art performance and improved generalization under complex degradation profiles.