AdaQual-Diff：基于扩散模型的自适应质量提示图像修复
AdaQual-Diff: Diffusion-Based Image Restoration via Adaptive Quality Prompting
AI总结：
针对传统图像修复方法难以适应复杂真实退化的局限，提出AdaQual-Diff框架，通过自适应质量提示机制将感知质量评估与扩散模型结合，动态分配计算资源实现细粒度修复，在多数据集上取得更优视觉效果。
摘要：
修复受复杂真实世界退化影响的图像仍具挑战性，因为传统方法往往无法适应存在的伪影的独特混合和严重程度。这源于对间接线索的依赖，这些线索难以捕捉真实的感知质量缺陷。为解决这一基本局限，我们引入AdaQual-Diff，这是一种基于扩散模型的框架，将感知质量评估直接集成到生成式修复过程中。我们的方法建立了DeQAScore区域质量分数与最优引导复杂度之间的数学关系，通过自适应质量提示机制实现。该机制根据测量的退化严重程度系统地调整提示结构：感知质量较低的区域接收计算密集、结构复杂且具有精确修复指令的提示，而质量较高的区域接收以保留而非干预为重点的最小提示。我们方法的技术核心在于与退化严重程度成比例的计算资源动态分配，创建一个空间变化的引导场，以数学精度指导扩散过程。通过将这种质量引导方法与特定内容条件相结合，我们的框架在不需要额外参数或推理迭代的情况下，实现了对区域修复强度的细粒度控制。实验结果表明，AdaQual-Diff在各种合成和真实世界数据集上实现了视觉上更优的修复效果。
英文摘要：
Restoring images afflicted by complex real-world degradations remains challenging, as conventional methods often fail to adapt to the unique mixture and severity of artifacts present. This stems from a reliance on indirect cues which poorly capture the true perceptual quality deficit. To address this fundamental limitation, we introduce AdaQual-Diff, a diffusion-based framework that integrates perceptual quality assessment directly into the generative restoration process. Our approach establishes a mathematical relationship between regional quality scores from DeQAScore and optimal guidance complexity, implemented through an Adaptive Quality Prompting mechanism. This mechanism systematically modulates prompt structure according to measured degradation severity: regions with lower perceptual quality receive computationally intensive, structurally complex prompts with precise restoration directives, while higher quality regions receive minimal prompts focused on preservation rather than intervention. The technical core of our method lies in the dynamic allocation of computational resources proportional to degradation severity, creating a spatially-varying guidance field that directs the diffusion process with mathematical precision. By combining this quality-guided approach with content-specific conditioning, our framework achieves fine-grained control over regional restoration intensity without requiring additional parameters or inference iterations. Experimental results demonstrate that AdaQual-Diff achieves visually superior restorations across diverse synthetic and real-world datasets.
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。
