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

2025-12-11

AI Summary

Existing all-in-one image restoration (AiOIR) methods lack explicit modeling of degradation types, limiting their effectiveness on complex or mixed degradations. To address this, we propose a unified adaptive restoration framework. First, we explicitly model degradation semantics via learnable clustering. Second, we design a probabilistic clustering-guided routing mechanism that decouples degradation identification from expert activation. Third, we introduce a degradation-aware frequency-domain modulation module that jointly propagates clustering cues in both spatial and frequency domains, enabling semantic-driven adaptive frequency decomposition and collaborative structural-textural enhancement. Our method achieves state-of-the-art performance across diverse single and mixed degradation scenarios—including blur, noise, and JPEG artifacts—demonstrating significant improvements in restoration fidelity and generalization capability.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

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.

Problem

• Unified framework for diverse image degradations
• Explicit modeling of degradation types and semantics
• Adaptive restoration for complex or mixed degradations

Innovation

• Cluster-guided routing mechanism for degradation recognition
• Frequency modulation module using cluster priors
• Bridging semantic cues with frequency-domain modulation