通过聚类引导实现统一图像修复，提升复杂退化场景下的恢复效果。
ClusIR: Towards Cluster-Guided All-in-One Image Restoration
- 用可学习聚类显式建模退化类型，分离识别与修复专家激活
- 跨空间与频域传播聚类提示，实现自适应修复
- 适合处理混合退化、需要统一框架的图像恢复任务
统一图像修复（AiOIR）旨在通过单一框架恢复多种退化图像。然而，现有方法常未能显式建模退化类型，且难以适应复杂或混合退化。为此，我们提出聚类引导图像修复框架ClusIR，通过可学习聚类显式建模退化语义，并在空间与频域间传播聚类感知提示以实现自适应修复。具体包含两个核心组件：概率聚类引导路由机制（PCGRM）和退化感知频域调制模块（DAFMM）。PCGRM将退化识别与专家激活解耦，实现判别性退化感知与稳定专家路由；DAFMM利用聚类引导先验进行自适应频域分解与定向调制，协同优化结构与纹理表示以提升恢复保真度。聚类引导的协同机制有效连接语义线索与频域调制，使ClusIR在多种退化场景下均取得显著性能。大量实验验证其在多个基准上的竞争力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。