Signal Processing - September 2017 - 172

Emerging Standards Awards from the
British Standard Institute.
Thomas Richter (richter@tik.uni-
stuttgart.de) received his M.S. degree in
physics, his M.S. degree in mathemat-
ics, and his Ph.D. degree in mathe-
matical physics in 1995, 1999, and
2000, respectively, from the Technical
University of Berlin, Germany. He is a
researcher at the TIK Computing Center
of the University of Stuttgart, Germany.
He has been a member of SC29WG1
since 2003.
To u r a d j Ebr a h i m i (Touradj.
Ebrahimi@epfl.ch) received his M.S.
degree in electrical engineering and his
Ph.D. degree in image and video coding
from École Polytechnique Fédérale de
Lausanne (EPFL), Switzerland, in 1989
and 1992, respectively. He is a profes-
sor at EPFL, heading its Multimedia
Signal Processing group. He is also the
convenor (chair) of the JPEG Stan -
dardization Committee.
Rafał K. Mantiuk (rkm38@cam
.ac.uk) received his M.S. degree in
computer science from the Technical

University of Szczecin, Poland, in 2003
and his Ph.D. degree in computer sci-
ence from the Max Planck Institute for
Computer Science, Germany, in 2006.
He is a senior lecturer at the Computer
Laboratory, University of Cambridge,
United Kingdom. He is the author of
a popular high dynamic range (HDR)
image quality metric, HDR-visual dif-
ference predictor-2, and the coauthor of
pfstools, software for high-dynamic range
image processing.

[5] A. Artusi, R. Mantiuk, R. Thomas, H. Philippe,
K. Pavel, A. Massimiliano, T. Arkady, and E.
Touradj, "Overview and evaluation of the JPEG XT
HDR image compression standard," Real Time Image
Process. J., pp. 1-16, Dec. 2015.

References

[9] E. Šikudova, T. Pouli, A. Artusi, A. Ahmet
Ogˇ uz, B. Francesco, E. Reinhard, and Z. M.
Mazlumoglu, "A gamut mapping framework for col-
or-accurate reproduction of HDR images," IEEE
Trans. Comput. Graph. Appl., vol. 36, no. 4, pp.
78-90, 2015.

[1] A. Artusi, F. Banterle, T. O. Aydin, D. Panozzo,
and O. Sork i ne -Hou r nu ng, Im age Content
Retargeting: Maintaining Color, Tone, and Spatial
Consistency. Boca Raton, FL: CRC, 2016.
[2] A. Artusi, R. Mantiuk, T. Richter, P. Korshunov,
P. Hanhart, T. Ebrahimi, and M. Agostinelli, "JPEG
XT: A compression standard for HDR and WCG
images," IEEE Signal Process. Mag., vol. 33, no. 2,
pp. 118-124, 2016.
[3] P. Debevec and J. Malik, "Recovering high
dynamic range radiance maps from photographs," in
Proc. 24th Annu. Conf. Computer Graphics and
Interactive Techniques, 1997, pp. 369-378.
[4] S. Pradeep and C. Aguerrebere, "Practical high
dynamic range imaging of everyday scenes:
Photographing the world as we see it with our own
eyes," IEEE Signal Process. Mag., vol. 33, no. 5, pp.
36-44, 2016.

[6] R. Thomas, A. Artusi, and E. Touradj, "JPEG
XT: A new family of JPEG backward-compatible
standards," IEEE Multimedia Mag., vol. 23, no. 3, pp.
80-88, 2016.
[7] R. Mantiuk, A. Efremov, K. Myszkowski, and
H.-P. Seidel, "Backward compatible high dynamic
range MPEG video compression," ACM Trans.
Graph., vol. 25, no. 3, pp. 713-723, 2006.
[8] T. Pouli, A. Artusi, F. Banterle, A. O. Akyüz,
H.-P. Seidel, and E. Reinhard, "Color correction for
tone reproduction," in Proc. Color and Imaging
Conf. Soc. Imaging Science and Technology, Nov.
2013, Albuquerque, NM, pp. 215-220.

[10] R. Mantiuk, R. Mantiuk, A. Tomaszewska, and
W. Heidrich, "Color correction for tone mapping,"
Comput. Graph. Forum, vol. 28, no. 2, pp. 193-202,
2009.
[11] M. Narwaria, R. K. Mantiuk, M. P. Da Silva, and
P. L. Callet, "HDR-VDP-2.2: A calibrated method for
objective quality prediction of high dynamic range and
standard images," J. Electron. Imaging, vol. 24, no. 1,
pp. 1-10, 2015.
[12] T. O. Aydin, R. Mantiuk, K. Myszkowski, and
H.-P. Seidel, "Dynamic range independent image
quality assessment," ACM Trans. Graph., vol. 27, no.
3, pp. 69:1-69:10, Aug. 2008.

Lei Zhang and Wangmeng Zuo

Image Restoration: From Sparse
and Low-Rank Priors to Deep Priors

T

he use of digital imaging devices,
ranging from professional digital
cinema cameras to consumer grade
smartphone cameras, has become ubiq-
uitous. The acquired image is a degraded
observation of the unknown latent image,
while the degradation comes from vari-
ous factors such as noise corruption,
camera shake, object motion, resolution
limit, hazing, rain streaks, or a combina-
Digital Object Identifier 10.1109/MSP.2017.2717489
Date of publication: 6 September 2017

172

tion of them. Image restoration (IR), as a
fundamental problem in image process-
ing and low-level vision, aims to recon-
struct the latent high-quality image from
its degraded observation. Image degrada-
tion is, in general, irreversible, and IR is
a typical ill-posed inverse problem. Due
to the large space of natural image con-
tents, prior information on image struc-
tures is crucial to regularize the solution
space and produce a good estimation
of the latent image. Image prior model-
ing and learning then are key issues in
IEEE SIGNAL PROCESSING MAGAZINE

|

September 2017

|

IR research. This lecture note describes
the development of image prior model-
ing and learning techniques, including
sparse representation models, low-rank
models, and deep learning models.

Relevance
IR plays an important role in many
applications, such as digital photogra-
phy, medical image analysis, remote
sensing, surveillance, and digital enter-
tainment. We give an introduction to the
major IR techniques developed in past
1053-5888/17©2017IEEE
http://www.stuttgart.de http://www.ac.uk
Table of Contents for the Digital Edition of Signal Processing - September 2017
