Face video restoration (FVR) is a challenging but important problem where one
seeks to recover a perceptually realistic face videos from a low-quality input.
While diffusion probabilistic models (DPMs) have been shown to achieve
remarkable performance for face image restoration, they often fail to preserve
temporally coherent, high-quality videos, compromising the fidelity of
reconstructed faces. We present a new conditional diffusion framework called
FLAIR for FVR. FLAIR ensures temporal consistency across frames in a
computationally efficient fashion by converting a traditional image DPM into a
video DPM. The proposed conversion uses a recurrent video refinement layer and
a temporal self-attention at different scales. FLAIR also uses a conditional
iterative refinement process to balance the perceptual and distortion quality
during inference. This process consists of two key components: a
data-consistency module that analytically ensures that the generated video
precisely matches its degraded observation and a coarse-to-fine image
enhancement module specifically for facial regions. Our extensive experiments
show superiority of FLAIR over the current state-of-the-art (SOTA) for video
super-resolution, deblurring, JPEG restoration, and space-time frame
interpolation on two high-quality face video datasets.

提出了一种名为 FLAIR 的条件扩散框架，用于解决人脸视频修复问题，并通过将传统的图像 DPM 转换为视频 DPM，通过递归视频细化层和不同尺度的时间自注意力来确保计算效率方面的时间一致性。FLAIR 还使用条件迭代细化过程来在推理过程中平衡感知和失真质量，包括通过数据一致性模块来确保生成的视频精确匹配观察结果，并通过面部区域的粗到精图像增强模块实现。广泛的实验证明 FLAIR 在视频的超分辨率、去模糊、JPEG 修复和空时帧插值等方面优于当前最先进的方法。