TY - GEN
T1 - Rolling Shutter Motion Deblurring
AU - Su, Shuochen
AU - Heidrich, Wolfgang
N1 - KAUST Repository Item: Exported on 2021-02-19
PY - 2015/10/15
Y1 - 2015/10/15
N2 - Although motion blur and rolling shutter deformations
are closely coupled artifacts in images taken with CMOS
image sensors, the two phenomena have so far mostly been
treated separately, with deblurring algorithms being unable
to handle rolling shutter wobble, and rolling shutter algorithms being incapable of dealing with motion blur.
We propose an approach that delivers sharp and undis
torted output given a single rolling shutter motion blurred
image. The key to achieving this is a global modeling of
the camera motion trajectory, which enables each scanline
of the image to be deblurred with the corresponding motion
segment. We show the results of the proposed framework
through experiments on synthetic and real data.
AB - Although motion blur and rolling shutter deformations
are closely coupled artifacts in images taken with CMOS
image sensors, the two phenomena have so far mostly been
treated separately, with deblurring algorithms being unable
to handle rolling shutter wobble, and rolling shutter algorithms being incapable of dealing with motion blur.
We propose an approach that delivers sharp and undis
torted output given a single rolling shutter motion blurred
image. The key to achieving this is a global modeling of
the camera motion trajectory, which enables each scanline
of the image to be deblurred with the corresponding motion
segment. We show the results of the proposed framework
through experiments on synthetic and real data.
UR - http://hdl.handle.net/10754/556518
UR - http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/1B_046.pdf
UR - http://www.scopus.com/inward/record.url?scp=84950262291&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2015.7298760
DO - 10.1109/CVPR.2015.7298760
M3 - Conference contribution
AN - SCOPUS:84950262291
SN - 9781467369640
SP - 1529
EP - 1537
BT - Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
PB - Institute of Electrical and Electronics Engineers (IEEE)
ER -