The differential equation-based image restoration approach aims to establish learnable trajectories connecting high-quality images to a tractable distribution, e.g., low-quality images or a Gaussian distribution. In this paper, we reformulate the trajectory optimization of this kind of method, focusing on enhancing both reconstruction quality and efficiency. Initially, we navigate effective restoration paths through a reinforcement learning process, gradually steering potential trajectories toward the most precise options. Additionally, to mitigate the considerable computational burden associated with iterative sampling, we propose cost-aware trajectory distillation to streamline complex paths into several manageable steps with adaptable sizes. Moreover, we fine-tune a foundational diffusion model (FLUX) with 12B parameters by using our algorithms, producing a unified framework for handling 7 kinds of image restoration tasks. Extensive experiments showcase the significant superiority of the proposed method, achieving a maximum PSNR improvement of 2.1 dB over state-of-the-art methods, while also greatly enhancing visual perceptual quality. Project page: \url{https://zhu-zhiyu.github.io/FLUX-IR/}.

翻译：基于微分方程的图像复原方法旨在建立从高质量图像到易处理分布（例如低质量图像或高斯分布）的可学习轨迹。本文重新阐述了此类方法的轨迹优化问题，重点关注提升重建质量与效率。首先，我们通过强化学习过程探索有效复原路径，逐步引导潜在轨迹向最精确方向收敛。此外，为减轻迭代采样带来的巨大计算负担，我们提出成本感知轨迹蒸馏方法，将复杂路径简化为若干具有自适应步长的可管理步骤。进一步地，我们运用所提算法对包含120亿参数的基础扩散模型（FLUX）进行微调，构建了能够处理7类图像复原任务的统一框架。大量实验表明，该方法具有显著优越性，在峰值信噪比指标上最高超越现有最优方法2.1分贝，同时大幅提升了视觉感知质量。项目页面：\url{https://zhu-zhiyu.github.io/FLUX-IR/}。