用强化学习优化图像修复路径，提升质量与效率。
Learning Efficient and Effective Trajectories for Differential Equation-based Image Restoration
- 通过强化学习寻找高效修复路径，逐步逼近最优解。
- 提出成本感知的路径蒸馏，将复杂过程压缩为可调步数。
- 基于120亿参数模型统一处理7类修复任务，效果显著。
基于微分方程的图像修复方法旨在建立从高质量图像到易处理分布（如低质量图像或高斯分布）的可学习轨迹。本文重新设计此类方法的轨迹优化策略，重点提升重建质量与计算效率。首先，利用强化学习逐步引导潜在轨迹向最优路径收敛；其次，为降低迭代采样的计算负担，提出成本感知的轨迹蒸馏方法，将复杂路径简化为若干可调节步数的轻量步骤；此外，使用所提算法对120亿参数的扩散模型FLUX进行微调，构建出统一框架以处理7类图像修复任务。大量实验表明，该方法在性能上显著优于现有技术，最大PSNR提升达2.1 dB，同时大幅改善视觉感知质量。
原文摘要 · Abstract (English)
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 $\textit{significant}$ 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: https://zhu-zhiyu.github.io/FLUX-IR/.
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。