While deep learning-based methods for blind face restoration have achieved unprecedented success, they still suffer from two major limitations. First, most of them deteriorate when facing complex degradations out of their training data. Second, these methods require multiple constraints, e.g., fidelity, perceptual, and adversarial losses, which require laborious hyper-parameter tuning to stabilize and balance their influences. In this work, we propose a novel method named DifFace that is capable of coping with unseen and complex degradations more gracefully without complicated loss designs. The key of our method is to establish a posterior distribution from the observed low-quality (LQ) image to its high-quality (HQ) counterpart. In particular, we design a transition distribution from the LQ image to the intermediate state of a pre-trained diffusion model and then gradually transmit from this intermediate state to the HQ target by recursively applying a pre-trained diffusion model. The transition distribution only relies on a restoration backbone that is trained with L1L_{1} loss on some synthetic data, which favorably avoids the cumbersome training process in existing methods. Moreover, the transition distribution can contract the error of the restoration backbone and thus makes our method more robust to unknown degradations. Comprehensive experiments show that DifFace is superior to current state-of-the-art methods, especially in cases with severe degradations. Code and model are available at https://github.com/zsyOAOA/DifFace.

中文翻译：

---

DifFace：具有扩散误差收缩的盲脸恢复


虽然基于深度学习的盲人面部恢复方法取得了前所未有的成功，但它们仍然存在两个主要局限性。首先，当面临训练数据的复杂退化时，它们中的大多数都会恶化。其次，这些方法需要多重约束，例如保真度、感知和对抗性损失，这需要费力的超参数调整来稳定和平衡它们的影响。在这项工作中，我们提出了一种名为 DifFace 的新颖方法，它能够更优雅地应对看不见的复杂退化，而无需复杂的损失设计。我们方法的关键是建立从观察到的低质量（LQ）图像到其高质量（HQ）对应图像的后验分布。特别是，我们设计了从 LQ 图像到预训练扩散模型的中间状态的转换分布，然后通过递归应用预训练扩散模型逐渐从该中间状态传输到 HQ 目标。转换分布仅依赖于在一些合成数据上使用 L1L_{1} 损失进行训练的恢复主干，这有利地避免了现有方法中繁琐的训练过程。此外，转移分布可以缩小恢复主干的误差，从而使我们的方法对未知的退化更加鲁棒。综合实验表明，DifFace 优于当前最先进的方法，特别是在严重退化的情况下。代码和模型可在 https://github.com/zsyOAOA/DifFace 获取。