MiM-DiT：基于扩散变换器的MoE在MoE中实现全功能图像修复
MiM-DiT: MoE in MoE with Diffusion Transformers for All-in-One Image Restoration
AI总结：
MiM-DiT通过双层MoE架构与预训练扩散模型，实现对多种图像退化类型的统一修复，提升复杂真实场景下的修复效果。
摘要：
全功能图像修复具有挑战性，因为不同的退化类型，如雾霾、模糊、噪声和低光照，对修复策略提出了多样化的要求，使单一模型难以有效处理。在本文中，我们提出了一种统一的图像修复框架，该框架集成了双层混合专家（MoE）架构与预训练的扩散模型。该框架在两个层面运行：Inter-MoE层自适应地结合专家组以处理主要的退化类型，而Intra-MoE层进一步选择专门的子专家以解决每种类型内的细微变化。这种设计使模型能够在多样化的退化类别之间实现粗粒度适应，同时对特定类内的细微变化进行精细调节，确保在处理复杂真实世界退化时具有高专业化。广泛的实验表明，所提出的方法在多个图像修复任务中优于最先进的方法。
英文摘要：
All-in-one image restoration is challenging because different degradation types, such as haze, blur, noise, and low-light, impose diverse requirements on restoration strategies, making it difficult for a single model to handle them effectively. In this paper, we propose a unified image restoration framework that integrates a dual-level Mixture-of-Experts (MoE) architecture with a pretrained diffusion model. The framework operates at two levels: the Inter-MoE layer adaptively combines expert groups to handle major degradation types, while the Intra-MoE layer further selects specialized sub-experts to address fine-grained variations within each type. This design enables the model to achieve coarse-grained adaptation across diverse degradation categories while performing fine-grained modulation for specific intra-class variations, ensuring both high specialization in handling complex, real-world corruptions. Extensive experiments demonstrate that the proposed method performs favorably against the state-of-the-art approaches on multiple image restoration task.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
