Face analysis lies at the heart of computer vision with remarkable progress in the past decades. Face recognition and tracking are tackled by building invariance to fundamental modes of variation such as illumination, 3D pose. A much less standing mode of variation is motion deblurring, which however presents substantial challenges in face analysis. Recent approaches either make oversimplifying assumptions, e.g. in cases of joint optimization with other tasks, or fail to preserve the highly structured shape/identity information. We introduce a two-step architecture tailored to the challenges of motion deblurring: the first step restores the low frequencies; the second restores the high frequencies, while ensuring that the outputs span the natural images manifold. Both steps are implemented with a supervised data-driven method; to train those we devise a method for creating realistic motion blur by averaging a variable number of frames. The averaged images originate from the $$2MF^2$$2MF2 dataset with $$19$$19 million facial frames, which we introduce for the task. Considering deblurring as an intermediate step, we conduct a thorough experimentation on high-level face analysis tasks, i.e. landmark localization and face verification, on blurred images. The experimental evaluation demonstrates the superiority of our method.

中文翻译：

---

面部运动去模糊

人脸分析是计算机视觉的核心，在过去的几十年里取得了显着的进步。人脸识别和跟踪是通过建立对基本变化模式（如照明、3D 姿势）的不变性来解决的。一种不太稳定的变化模式是运动去模糊，但这在面部分析中提出了重大挑战。最近的方法要么做出过于简单化的假设，例如在与其他任务联合优化的情况下，要么无法保留高度结构化的形状/身份信息。我们引入了一种针对运动去模糊挑战量身定制的两步架构：第一步恢复低频；第二个恢复高频，同时确保输出跨越自然图像流形。这两个步骤都是通过有监督的数据驱动方法实现的；为了训练这些，我们设计了一种方法，通过平均可变数量的帧来创建逼真的运动模糊。平均图像来自 $$2MF^2$$2MF2 数据集，其中包含 $19$1900 万美元的面部帧，我们为该任务引入了该数据集。考虑将去模糊作为中间步骤，我们对模糊图像的高级人脸分析任务（即地标定位和人脸验证）进行了彻底的实验。实验评估证明了我们方法的优越性。模糊图像上的地标定位和人脸验证。实验评估证明了我们方法的优越性。模糊图像上的地标定位和人脸验证。实验评估证明了我们方法的优越性。