Image restoration is a fundamental problem that involves recovering a high-quality clean image from its degraded observation. All-In-One image restoration models can effectively restore images from various types and levels of degradation using degradation-specific information as prompts to guide the restoration model. In this work, we present the first approach that uses human-written instructions to guide the image restoration model. Given natural language prompts, our model can recover high-quality images from their degraded counterparts, considering multiple degradation types. Our method, InstructIR, achieves state-of-the-art results on several restoration tasks including image denoising, deraining, deblurring, dehazing, and (low-light) image enhancement. InstructIR improves +1dB over previous all-in-one restoration methods. Moreover, our dataset and results represent a novel benchmark for new research on text-guided image restoration and enhancement. Our code, datasets and models are available at: https://github.com/mv-lab/InstructIR

翻译：图像复原是一个基础性问题，涉及从退化观测中恢复出高质量清晰图像。全合一图像复原模型能够利用退化特定信息作为提示来引导复原模型，从而有效处理多种类型和级别的退化。在本工作中，我们首次提出了一种使用人类撰写的指令来指导图像复原模型的方法。基于自然语言提示，我们的模型可以从退化图像中恢复出高质量图像，并同时考虑多种退化类型。我们的方法 InstructIR 在多个复原任务（包括图像去噪、去雨、去模糊、去雾及（低光照）图像增强）上均取得了最优结果。相比先前的全合一复原方法，InstructIR 的指标提升了+1dB。此外，我们的数据集和结果为基于文本引导的图像复原与增强的新研究提供了新颖基准。我们的代码、数据集和模型可在 https://github.com/mv-lab/InstructIR 获取。