Degradation Frequency Curve: An Explicit Frequency-Quantified Representation for All-in-One Image Restoration

TL;DR

This paper introduces the Degradation Frequency Curve (DFC), a spectral representation that explicitly quantifies image degradation, enabling more effective and generalizable all-in-one blind image restoration.

Contribution

The paper proposes DFC as a novel spectral representation for degradation, and develops DFC-IR, a framework that uses DFCs for improved restoration across diverse degradation types.

Findings

DFC achieves state-of-the-art results on multiple benchmarks.

DFC provides a measurable and adaptable degradation coordinate space.

DFC-IR demonstrates superior generalization to unseen degradations.

Abstract

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.