Recent advancements in all-in-one image restoration models have revolutionized the ability to address diverse degradations through a unified framework. However, parameters tied to specific tasks often remain inactive for other tasks, making mixture-of-experts (MoE) architectures a natural extension. Despite this, MoEs often show inconsistent behavior, with some experts unexpectedly generalizing across tasks while others struggle within their intended scope. This hinders leveraging MoEs' computational benefits by bypassing irrelevant experts during inference. We attribute this undesired behavior to the uniform and rigid architecture of traditional MoEs. To address this, we introduce ``complexity experts" -- flexible expert blocks with varying computational complexity and receptive fields. A key challenge is assigning tasks to each expert, as degradation complexity is unknown in advance. Thus, we execute tasks with a simple bias toward lower complexity. To our surprise, this preference effectively drives task-specific allocation, assigning tasks to experts with the appropriate complexity. Extensive experiments validate our approach, demonstrating the ability to bypass irrelevant experts during inference while maintaining superior performance. The proposed MoCE-IR model outperforms state-of-the-art methods, affirming its efficiency and practical applicability. The source code and models are publicly available at \href{https://eduardzamfir.github.io/moceir/}{\texttt{eduardzamfir.github.io/MoCE-IR/}}

翻译：近期，一体化图像复原模型的进展彻底革新了通过统一框架处理多种退化类型的能力。然而，针对特定任务的参数在处理其他任务时往往处于非激活状态，这使得专家混合（MoE）架构成为一种自然的扩展。尽管如此，MoE模型常表现出不一致的行为：部分专家意外地展现出跨任务泛化能力，而另一些专家则在其预期范围内表现不佳。这阻碍了在推理过程中通过绕过无关专家来利用MoE计算优势的可能性。我们将这种非理想行为归因于传统MoE架构的均匀性与刚性。为此，我们提出“复杂度专家”——一种具有可变计算复杂度与感受野的灵活专家模块。核心挑战在于如何为每个专家分配任务，因为退化复杂度通常是未知的。因此，我们在执行任务时引入对低复杂度的简单偏好。令人惊讶的是，这种偏好能有效驱动任务特异性分配，将任务分配给具有适当复杂度的专家。大量实验验证了我们的方法，证明其能在推理过程中绕过无关专家，同时保持卓越性能。所提出的MoCE-IR模型超越了现有最优方法，证实了其效率与实用价值。源代码与模型已公开于 \href{https://eduardzamfir.github.io/moceir/}{\texttt{eduardzamfir.github.io/MoCE-IR/}}。