Abstract
Deep learning methods have state-of-the-art performances in many image restoration tasks. Their effectiveness is mostly related to the size of the dataset used for the training. Deep image prior (DIP) is an energy-function framework which eliminates the dependency on the training set, by considering the structure of a neural network as an handcrafted prior offering high impedance to noise and low impedance to signal. In this paper, we analyze and compare the use of different optimization schemes inside the DIP framework for the denoising task.
Issue Section:
Research Papers
References
1.
Scherzer
,
O.
,
Grasmair
,
M.
,
Grossauer
,
H.
,
Haltmeier
,
M.
, and
Lenzen
,
F.
, 2009
, Variational Methods in Imaging
,
Springer
,
New York
.2.
Arridge
,
S.
,
Maass
,
P.
,
Öktem
,
O.
, and
Schönlieb
,
C.-B.
, 2019
, “
Solving Inverse Problems Using Data-Driven Models
,” Acta Numerica
,
28
, pp. 1
–174
.10.1017/S09624929190000593.
Jin
,
K. H.
,
McCann
,
M. T.
,
Froustey
,
E.
, and
Unser
,
M.
, 2017
, “
Deep Convolutional Neural Network for Inverse Problems in Imaging
,” IEEE Trans. Image Process.
,
26
(9
), pp. 4509
–4522
.10.1109/TIP.2017.27130994.
Ulyanov
,
D.
,
Vedaldi
,
A.
, and
Lempitsky
,
V.
, 2018
, “
Deep Image Prior
,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
,
Salt Lake City, UT
, June 18–23, pp. 9446
–9454
.5.
Heckel
,
R.
, and
Hand
,
P.
, 2019
, “
Deep Decoder: Concise Image Representations From Untrained Non-Convolutional Networks
,” International Conference on Learning Representations.6.
Dittmer
,
S.
,
Kluth
,
T.
,
Maass
,
P.
, and
Baguer
,
D. O.
, 2020
, “
Regularization by Architecture: A Deep Prior Approach for Inverse Problems
,” J. Math. Imaging Vision
,
62
(3
), pp. 456
–470
.10.1007/s10851-019-00923-x7.
Cheng
,
Z.
,
Gadelha
,
M.
,
Maji
,
S.
, and
Sheldon
,
D.
, 2019
, “
A Bayesian Perspective on the Deep Image Prior
,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
,
Long Beach, CA
, June 15–20, pp. 5443
–5451
.https://openaccess.thecvf.com/content_CVPR_2019/papers/Cheng_A_Bayesian_Perspective_on_the_Deep_Image_Prior_CVPR_2019_paper.pdf8.
Sagel
,
A.
,
Roumy
,
A.
, and
Guillemot
,
C.
, 2020
, “
Sub-Dip: Optimization on a Subspace With Deep Image Prior Regularization and Application to Superresolution
,” ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP
),
Barcelona, Spain
, May 4–8, pp. 2513
–2517
.10.1109/ICASSP40776.2020.90542709.
Mataev
,
G.
,
Milanfar
,
P.
, and
Elad
,
M.
, 2019
, “
DeepRED: Deep Image Prior Powered by RED
,” Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV
) Workshops.https://openaccess.thecvf.com/content_ICCVW_2019/papers/LCI/Mataev_DeepRED_Deep_Image_Prior_Powered_by_RED_ICCVW_2019_paper.pdf10.
Liu
,
J.
,
Sun
,
Y.
,
Xu
,
X.
, and
Kamilov
,
U. S.
, 2019
, “
Image Restoration Using Total Variation Regularized Deep Image Prior
,” ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP
),
Brighton, UK
,
May 12–17
, pp. 7715
–7719
.10.1109/ICASSP.2019.868285611.
Cascarano
,
P.
,
Sebastiani
,
A.
,
Comes
,
M. C.
,
Franchini
,
G.
, and
Porta
,
F.
, 2021
, “
Combining Weighted Total Variation and Deep Image Prior for Natural and Medical Image Restoration via ADMM
,” 2021 21st International Conference on Computational Science and Its Applications (ICCSA)
,
Cagliari, Italy
, Sept. 13–16, pp. 39
–46
.10.1109/ICCSA54496.2021.0001612.
Cascarano
,
P.
,
Comes
,
M. C.
,
Mencattini
,
A.
,
Parrini
,
M. C.
,
Piccolomini
,
E. L.
, and
Martinelli
,
E.
, 2021
, “
Recursive Deep Prior Video: A Super Resolution Algorithm for Time-Lapse Microscopy of Organ-on-Chip Experiments
,” Med. Image Anal.
,
72
, p. 102124
.10.1016/j.media.2021.10212413.
Kingma
,
D.
, and
Ba
,
J.
, 2017
, “
Adam: A Method for Stochastic Optimization
,” e-print arXiv:1412.6980.14.
Bertsekas
,
D. P.
, “Nonlinear Programming
,”
J. Operational Res. Soc., 48(3), pp. 334
–334
.15.
Robbins
,
H.
, and
Monro
,
S.
, 1951
, “
A Stochastic Approximation Method
,” Ann. Math. Stat.
,
22
(3
), pp. 400
–407
.10.1214/aoms/117772958616.
Bottou
,
L.
,
Curtis
,
F.
, and
Nocedal
,
J.
, 2018
, “
Optimization Methods for Large-Scale Machine Learning
,” SIAM Rev.
,
60
(2
), pp. 223
–311
.10.1137/16M108017317.
Loizou
,
N.
, and
Richtarik
,
P.
, 2018
, “
Momentum and Stochastic Momentum for Stochastic Gradient, Newton, Proximal Point and Subspace Descent Methods
,” Comput. Optimization Appl
., 77(3), pp. 653
–710
.10.1007/s10589-020-00220-z18.
Chakrabarty
,
P.
, and
Maji
,
S.
, 2019
, “
The Spectral Bias of the Deep Image Prior
,” e-print arXiv:1912.08905.Copyright © 2022 by ASME
You do not currently have access to this content.
