Generative diffusion models can serve as a prior which ensures that solutions of image restoration systems adhere to the manifold of natural images. However, for restoring facial images, a personalized prior is necessary to accurately represent and reconstruct unique facial features of a given individual. In this paper, we propose a simple, yet effective, method for personalized restoration, called Dual-Pivot Tuning - a two-stage approach that personalize a blind restoration system while maintaining the integrity of the general prior and the distinct role of each component. Our key observation is that for optimal personalization, the generative model should be tuned around a fixed text pivot, while the guiding network should be tuned in a generic (non-personalized) manner, using the personalized generative model as a fixed ``pivot". This approach ensures that personalization does not interfere with the restoration process, resulting in a natural appearance with high fidelity to the person's identity and the attributes of the degraded image. We evaluated our approach both qualitatively and quantitatively through extensive experiments with images of widely recognized individuals, comparing it against relevant baselines. Surprisingly, we found that our personalized prior not only achieves higher fidelity to identity with respect to the person's identity, but also outperforms state-of-the-art generic priors in terms of general image quality. Project webpage: https://personalized-restoration.github.io

翻译：生成扩散模型可作为先验知识，确保图像恢复系统的解符合自然图像流形。然而，在面部图像恢复中，需要个性化先验来准确表征和重建特定个体的独特面部特征。本文提出一种简洁高效的个性化恢复方法——双枢轴调优（Dual-Pivot Tuning），该两阶段方法在保持通用先验完整性与各组件独特作用的同时，实现盲恢复系统的个性化适配。核心发现是：为达到最优个性化效果，生成模型应围绕固定文本枢轴进行微调，而引导网络则需采用通用（非个性化）方式微调，并以个性化生成模型作为固定“枢轴”。这种设计确保个性化过程不干扰恢复流程，从而在忠实还原人物身份特征与退化图像属性的同时，形成自然外观。我们通过对知名人物图像的定性定量实验，与相关基线方法进行对比验证。令人惊讶的是，个性化先验不仅能更精确地保持人物身份特征，在通用图像质量指标上也超越了当前最先进的通用先验方法。项目主页：https://personalized-restoration.github.io