ProRes：探索面向通用图像复原的退化感知视觉提示
ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration
AI总结：
本文提出ProRes，一种基于退化感知视觉提示的通用图像复原模型，利用ViT实现可控复原，并通过提示调优适应新任务，性能媲美任务特定方法。
摘要：
图像复原旨在重建退化图像，例如去噪或去模糊。现有工作侧重于设计特定任务的方法，而对通用方法的尝试不足。然而，简单地将多个任务统一到一个通用架构中会导致不可控且不期望的预测。为解决这些问题，我们探索了通用架构中用于图像复原任务的提示学习。在本文中，我们提出了退化感知视觉提示，将各种类型的图像退化（如噪声和模糊）编码为统一的视觉提示。这些退化感知提示提供了对图像处理的控制，并允许加权组合以实现定制化的图像复原。随后，我们利用退化感知视觉提示构建了一个可控且通用的图像复原模型，称为ProRes，它适用于广泛的图像复原任务。ProRes利用普通的Vision Transformer（ViT），无需任何任务特定的设计。此外，预训练的ProRes可以通过高效的提示调优，仅使用少量图像即可轻松适应新任务。无需额外技巧，ProRes在性能上与任务特定方法相比具有竞争力，实验证明了其在可控复原和新任务适应方面的能力。代码和模型将在\(\url{https://github.com/leonmakise/ProRes}\)发布。
英文摘要：
Image restoration aims to reconstruct degraded images, e.g., denoising or deblurring. Existing works focus on designing task-specific methods and there are inadequate attempts at universal methods. However, simply unifying multiple tasks into one universal architecture suffers from uncontrollable and undesired predictions. To address those issues, we explore prompt learning in universal architectures for image restoration tasks. In this paper, we present Degradation-aware Visual Prompts, which encode various types of image degradation, e.g., noise and blur, into unified visual prompts. These degradation-aware prompts provide control over image processing and allow weighted combinations for customized image restoration. We then leverage degradation-aware visual prompts to establish a controllable and universal model for image restoration, called ProRes, which is applicable to an extensive range of image restoration tasks. ProRes leverages the vanilla Vision Transformer (ViT) without any task-specific designs. Furthermore, the pre-trained ProRes can easily adapt to new tasks through efficient prompt tuning with only a few images. Without bells and whistles, ProRes achieves competitive performance compared to task-specific methods and experiments can demonstrate its ability for controllable restoration and adaptation for new tasks. The code and models will be released in \url{https://github.com/leonmakise/ProRes}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
