ClusIR: Towards Cluster-Guided All-in-One Image Restoration

TL;DR

ClusIR introduces a cluster-guided framework for all-in-one image restoration, explicitly modeling degradation types and adaptively restoring images across various degradation scenarios using novel clustering and frequency modulation techniques.

Contribution

The paper proposes a novel ClusIR framework with learnable clustering and frequency modulation modules for explicit degradation modeling and adaptive restoration.

Findings

Achieves competitive results across multiple benchmarks.

Effectively models complex and mixed degradations.

Demonstrates improved restoration fidelity.

Abstract

All-in-One Image Restoration (AiOIR) aims to recover high-quality images from diverse degradations within a unified framework. However, existing methods often fail to explicitly model degradation types and struggle to adapt their restoration behavior to complex or mixed degradations. To address these issues, we propose ClusIR, a Cluster-Guided Image Restoration framework that explicitly models degradation semantics through learnable clustering and propagates cluster-aware cues across spatial and frequency domains for adaptive restoration. Specifically, ClusIR comprises two key components: a Probabilistic Cluster-Guided Routing Mechanism (PCGRM) and a Degradation-Aware Frequency Modulation Module (DAFMM). The proposed PCGRM disentangles degradation recognition from expert activation, enabling discriminative degradation perception and stable expert routing. Meanwhile, DAFMM leverages the cluster-guided priors to perform adaptive frequency decomposition and targeted modulation, collaboratively refining structural and textural representations for higher restoration fidelity. The cluster-guided synergy seamlessly bridges semantic cues with frequency-domain modulation, empowering ClusIR to attain remarkable restoration results across a wide range of degradations. Extensive experiments on diverse benchmarks validate that ClusIR reaches competitive performance under several scenarios.