Motion Deblurring of Faces

Chrysos, Grigorios; Favaro, Paolo; Zafeiriou, Stefanos (2018). Motion Deblurring of Faces. International journal of computer vision, 127(6-7), pp. 801-823. Springer 10.1007/s11263-018-1138-7

Preview

Text Chrysos2018_Article_MotionDeblurringOfFaces.pdf - Published Version Available under License Creative Commons: Attribution (CC-BY). Download (4MB) | Preview

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 2M F² dataset with 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, onblurred images. The experimental evaluation demonstrates the superiority of our method.

Interest & Impact

Downloads

108 since deposited on 28 May 2019
23 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item