Blind face restoration usually synthesizes degraded low-quality data with a pre-defined degradation model for training, while more complex cases could happen in the real world. This gap between the assumed and actual degradation hurts the restoration performance where artifacts are often observed in the output. However, it is expensive and infeasible to include every type of degradation to cover real-world cases in the training data. To tackle this robustness issue, we propose Diffusion-based Robust Degradation Remover (DR2) to first transform the degraded image to a coarse but degradation-invariant prediction, then employ an enhancement module to restore the coarse prediction to a high-quality image. By leveraging a well-performing denoising diffusion probabilistic model, our DR2 diffuses input images to a noisy status where various types of degradation give way to Gaussian noise, and then captures semantic information through iterative denoising steps. As a result, DR2 is robust against common degradation (e.g. blur, resize, noise and compression) and compatible with different designs of enhancement modules. Experiments in various settings show that our framework outperforms state-of-the-art methods on heavily degraded synthetic and real-world datasets.

翻译：盲脸恢复通常使用预定义的退化模型合成退化的低质量数据进行训练，但现实世界中可能出现更复杂的情况。这种假设退化与实际退化之间的差距会损害恢复性能，输出中常出现伪影。然而，在训练数据中涵盖所有类型的退化以覆盖真实场景既昂贵又不可行。为解决这一鲁棒性问题，我们提出基于扩散的鲁棒退化移除器（DR2），首先将退化图像转化为粗糙但退化不变的预测，随后使用增强模块将粗糙预测恢复为高质量图像。通过利用性能优异的去噪扩散概率模型，我们的DR2将输入图像扩散至噪声状态，在此状态下各类退化让位于高斯噪声，然后通过迭代去噪步骤捕获语义信息。因此，DR2对常见退化（如模糊、缩放、噪声和压缩）具有鲁棒性，并能兼容不同设计的增强模块。多组实验表明，我们的框架在高度退化的合成数据集和真实数据集上均优于现有最先进方法。