We present AutoDIR, an innovative all-in-one image restoration system incorporating latent diffusion. AutoDIR excels in its ability to automatically identify and restore images suffering from a range of unknown degradations. AutoDIR offers intuitive open-vocabulary image editing, empowering users to customize and enhance images according to their preferences. Specifically, AutoDIR consists of two key stages: a Blind Image Quality Assessment (BIQA) stage based on a semantic-agnostic vision-language model which automatically detects unknown image degradations for input images, an All-in-One Image Restoration (AIR) stage utilizes structural-corrected latent diffusion which handles multiple types of image degradations. Extensive experimental evaluation demonstrates that AutoDIR outperforms state-of-the-art approaches for a wider range of image restoration tasks. The design of AutoDIR also enables flexible user control (via text prompt) and generalization to new tasks as a foundation model of image restoration. Project is available at: \url{https://jiangyitong.github.io/AutoDIR_webpage/}.

翻译：本文提出AutoDIR，一种创新的集成潜在扩散技术的一体化图像复原系统。AutoDIR 具备自动识别并修复遭受多种未知退化图像的能力。该系统提供直观的开放词汇图像编辑功能，使用户能够根据个人偏好自定义和增强图像。具体而言，AutoDIR 包含两个关键阶段：基于语义无关视觉语言模型的盲图像质量评估阶段，该阶段自动检测输入图像的未知退化类型；以及一体化图像复原阶段，该阶段利用结构校正的潜在扩散模型来处理多种类型的图像退化。大量实验评估表明，AutoDIR 在更广泛的图像复原任务上超越了现有最先进方法。AutoDIR 的设计还支持灵活的用户控制（通过文本提示），并能作为图像复原的基础模型泛化至新任务。项目地址：\url{https://jiangyitong.github.io/AutoDIR_webpage/}。