Imperial College London


Faculty of EngineeringDepartment of Computing

Professor in Machine Learning & Computer Vision



+44 (0)20 7594 8461s.zafeiriou Website CV




375Huxley BuildingSouth Kensington Campus






BibTex format

author = {Chrysos, GG and Favaro, P and Zafeiriou, S},
doi = {10.1007/s11263-018-1138-7},
journal = {International Journal of Computer Vision},
pages = {801--823},
title = {Motion deblurring of faces},
url = {},
volume = {127},
year = {2019}

RIS format (EndNote, RefMan)

AB - 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.
AU - Chrysos,GG
AU - Favaro,P
AU - Zafeiriou,S
DO - 10.1007/s11263-018-1138-7
EP - 823
PY - 2019///
SN - 0920-5691
SP - 801
TI - Motion deblurring of faces
T2 - International Journal of Computer Vision
UR -
UR -
VL - 127
ER -