Motion deblurring of faces
File(s)
Published version
Author(s)
Chrysos, GG
Favaro, P
Zafeiriou, S
Type
Journal Article
Abstract
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 2 MF2 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, on blurred images. The experimental evaluation demonstrates the superiority of our method.
Date Issued
2019-06-01
Date Acceptance
2018-11-26
Citation
International Journal of Computer Vision, 2019, 127 (6-7), pp.801-823
ISSN
0920-5691
Publisher
Springer US
Start Page
801
End Page
823
Journal / Book Title
International Journal of Computer Vision
Volume
127
Issue
6-7
Copyright Statement
© 2018 The Author(s) Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
License URL
Subjects
Science & Technology
Technology
Computer Science, Artificial Intelligence
Computer Science
Learning motion deblurring
Face deblurring
Data-driven networks
IMAGE
IDENTIFICATION
RESTORATION
cs.CV
cs.CV
Artificial Intelligence & Image Processing
0801 Artificial Intelligence and Image Processing
Publication Status
Published
Date Publish Online
2018-12-17