Altmetric

Motion deblurring of faces

File Description SizeFormat 
Chrysos2018_Article_MotionDeblurringOfFaces.pdfPublished version4.61 MBAdobe PDFView/Open
Title: Motion deblurring of faces
Authors: Chrysos, GG
Favaro, P
Zafeiriou, S
Item 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.
Issue Date: 17-Dec-2018
Date of Acceptance: 26-Nov-2018
URI: http://hdl.handle.net/10044/1/69747
DOI: https://dx.doi.org/10.1007/s11263-018-1138-7
ISSN: 0920-5691
Journal / Book Title: International Journal of Computer Vision
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.
Keywords: cs.CV
0801 Artificial Intelligence and Image Processing
Artificial Intelligence & Image Processing
Publication Status: Published online
Online Publication Date: 2018-12-17
Appears in Collections:Computing



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons