A Technical Seminar-I Report on

Foundations of computational imaging

Submitted in partial fulfilment of the Academic requirements for the award of the degree of

Bachelor of Technology

In
Electronics & Communication Engineering

Submitted by

KUDARAVALLI BHARGAV (21H51A0416)

Under the Esteemed Guidance of

Mrs. Dr. Y. ARUNA SUHASINI

(Associate Professor)

DEPARTMENT OF ELECTRONICS & COMMUNICATION ENGINEERING

CMR COLLEGE OF ENGINEERING & TECHNOLOGY

(Autonomous) (NAAC Accredited with ‘A+’ Grade &
NBA Accredited)
(Approved by AICTE, Permanently Affiliated to JNTU Hyderabad) KANDLAKOYA, MEDCHAL
ROAD, HYDERABAD – 501401

[i]
 2023-24

CMR COLLEGE OF ENGINEERING & TECHNOLOGY

(Autonomous)
(NAAC Accredited with ‘A+’ Grade & NBA Accredited) (Approved by AICTE, Permanently
Affiliated to JNTU Hyderabad) KANDLAKOYA, MEDCHAL ROAD, HYDERABAD - 501401

DEPARTMENT OF ELECTRONICS & COMMUNICATION ENGINEERING

CERTIFICATE

This is to certify that the Technical Seminar-I report entitled “FOUNDATIONS OF

COMPUTATIONAL IMAGING” is a bonafide work done by K. BHARGAV (21H51A0416)
in partial fulfilment of the requirements for the award of the degree of Bachelor of Technology
in Electronics & Communication Engineering from CMR College of Engineering & Technology,
Hyderabad, Telangana is record of bonafide work carried during the Academic Year 2023-24.

Under the guidance of

INTERNAL GUIDE Head of the Department

DR.Y. ARUNA SUHASINI Dr. P. RAVEENDRA BABU
(Associate professor) Professor & Head of Dept of ECE, CMRCET

[ii]
 ACKNOWLEDGEMENT

With great pleasure I want to take this opportunity to express my gratitude to all the people who
helped in making this technical seminar-I a grand success.
I am grateful to Mrs. Dr. Y. Aruna Suhasini for her valuable suggestions and guidance given
by them during the execution of this technical seminar-I.
I would like to thank Dr. P. RAVEENDRA BABU, Head of the Department of Electronics
and Communication Engineering, for being moral support throughout the period of my study in
CMR College of Engineering & Technology.
I am very grateful to Dr. Ghanta Devadasu, Dean-Academics, CMR College of
Engineering and Technology, for his constant support and motivation in carrying out the technical
seminar-I work successfully.
I express my deep sense of gratitude to Principal, Major Dr. V.A. Narayana for his constant
support throughout my technical seminar-I.
I would like to thank the Teaching & Non- Teaching staff of ECE Department for sharing
their knowledge with me.
Last but not the least I express my sincere thanks to Sri. Ch. Gopal Reddy garu, Secretary &
Correspondent, CMR Group of Institutions, for his continuous care towards my
achievements.

KUDARAVALLI BHARGAV
(21H51A0416)

[iii]
 ABSTRACT

Twenty-five years ago, the field of computational imaging arguably did not exist, at

least not as a standalone arena of research activity and technical development. Of

course, the idea of using computation to form images had been around for several

decades, largely thanks to the development of medical imaging—such as magnetic

resonance imaging (MRI) and X-ray tomography—in the 1970s and synthetic-aperture

radar (SAR) even earlier. Yet, a quarter of a century ago, such technologies would

have been considered to be a sub focus of the wider field of image processing. This

view started to change, however, in the late 1990s with a series of innovations that

established computational imaging as a scientific and technical pursuit in its own right.

[iv]
 INDEX
S.No. CONTENTS Page No.

ABSTRACT v
Chapter 1 INTRODUCTION 1
1.1 Introduction 2
1.2 History 3-4
Chapter 2 LITRETURE REVIEW 5-8
Chapter 3 PHYSICS DRIVEN IMAGING 9

3.1 Analog cameras 10

3.2 X-ray tomography 11-12

3.3 MRI 13

3.4 Spot light mode: SAR 14-15

Chapter 4 MBIR: THE RISE OF COMPUTATIONAL 16
IMAGING
4.1 Image formation as optimization 17-18

4.2 Focus on prior models 19-20

4.3 Optimization algorithms 21-22
Chapter 5 LEARNING BASED FILTERS 23
5.1 Estimate post-processing 24
5.2 Data preprocessing 25
5.3 Learned explicit priors 26-27
5.4 Learned inverse mappings 28
Chapter 6 SPS INVOLVEMENT 29-31
6.1 Advantages and Disadvantages 32
6.2 Applications 33
Chapter 7 CONCLUSION 34
7.1 Conclusion 35
7.2 References 36-42

[v]
 COMPUTATIONAL IMAGING

CHAPTER-1
INTRODUCTION

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 1

 COMPUTATIONAL IMAGING

1.1 INTRODUCTION OF COMPUTATIONAL IMAGING

Twenty-five years ago, the field of computational imaging arguably did not exist, at least not
as a standalone arena of research activity and technical development. Of course, the idea
of using computation to form images had been around for several decades, largely thanks
to the development of medical imaging—such as magnetic resonance imaging (MRI) and X-
ray tomography—in the 1970s and synthetic-aperture radar (SAR) even earlier. Yet, a
quarter of a century ago, such technologies would have been considered to be a sub focus
of the wider field of image processing. This view started to change, however, in the late
1990s with a series of innovations that established computational imaging as a scientific
and technical pursuit in its own right.

In this article, I provide a signal processing perspective on the area of computational

imaging, focusing on its emergence and evolution within the signal processing community.
First, in the “Historical Perspective” section, I present an overview of the technical
development of computational imaging wherein i trace the historical development of the
field from its origins through to the present day. Then, in the “Signal Processing Society
Involvement” section, I provide a brief overview of the involvement of the IEEE Signal
Processing Society (SPS) in the field. Finally, in the “Conclusions” section, I make several
concluding remarks

1.2 HISTORY OF COMPUTATIONAL IMAGING

I begin my discourse by tracing the history of computational image formation. I start this
historical perspective with its origins in physics-dependent imaging and then proceed to
model-based imaging, including the impact of priors and sparsity. I next progress to recent
data-driven and learning-based image formations, finally coming full circle back to how
physics-based models are being merged with big data and machine learning for improved
outcomes.

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 2

 COMPUTATIONAL IMAGING

Computational imaging can be defined in a number of ways, but for the purposes of the
present article, I define it as the creation of an image from measurements wherein
computation plays an integral role in the image-formation process. In contrast to historical
“standard” imaging in which optics play the central role in image formation, in
computational imaging, it is computation, in the form of algorithms running on computers,
that assumes the primary burden of producing images. Well-known examples would include
X-ray-based tomography, SAR, and MRI. In such cases, the data produced by the sensing
instrument are generally not images, and thus, require processing to produce the desired
useful output in the form of an image. To fix ideas and notation, I denote the unknown but
desired image by , x belongs to Rn such that x contains N pixels. In my problem of interest, I
cannot directly observe , x but instead observe a set of data , y RM ! which has been
measured through a process
connected to a sensor . C This relationship can be represented mathematically by

(Y)=C(x)+n

where n is a noise signal. The goal of computational imaging is then to estimate the image x
from knowledge of both the data y as well as the imaging system or measurement process, ,
C i.e., it naturally involves solving an inverse problem. Several examples of computational
imaging are depicted in Figure 1, illustrating their sensing process and resulting images.

For many common imaging problems, C in (1) is (or can be well approximated by) a linear
operator, i.e., a matrix, such that

C(x)=Cx, C belongs to R m*n

In this case, when C is invertible and well-conditioned, the inverse problem is

mathematically straight forward, although even in this case, it is often computationally

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 3

 COMPUTATIONAL IMAGING

challenging due to the size of the problem. For example, an image of modest size—say,
1024*1024-corresponds to an x with 1 million variables and a C with 10 2 elements. The
inverse problem becomes even more difficult when C is an ill-conditioned matrix or a
nonlinear operator or produces an observation y with fewer samples than the number of
unknowns in x.

In the sequel, I provide a roughly chronological road map of computational imaging from a
signal processing perspective. Four broad domains, will be discussed in turn: physics-driven
imaging, model-based image reconstruction (MBIR), data-driven models and learning, and
learning-based filters and algorithms. M topic concludes with current-day algorithmic
methods that effectively join back up to the left, i.e., techniques that couple physical models
with learned prior information through algorithms.

CHAPTER -2
LITERATURE REVIEW
2.1 INTERACTIVE FAULT EXTRACTION IN 3D SEISMIC DATA
USING THE HOUGH TRANSFORM AND TRACKING VECTORS

In this paper, we introduced a method that semiautomatically detects faults using the Hough
transform as well as tracking vectors. To improve the efficiency of fault interpretation, we
classified seismic sections into reference and predicted sections by borrowing the concept of

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 4

 COMPUTATIONAL IMAGING

I- and B-frames in video-coding techniques and applied different strategies on the two types
of sections. In reference sections, we first highlighted likely fault regions on the basis of
discontinuity maps and employed the Hough transform to extract the features of faults.
After removing false features, we optimally connected remaining features by involving
geological constraints. In predicted sections, the proposed tracking method synthesizes
tracked faults based on detected faults projected from reference sections. In the tracking
process, we estimated tracking vectors using discontinuity information and optimally
combined projected faults. To evaluate the performance of the proposed method, we
introduced the fault similarity (FauSIM) index that describes the similarity between detected
faults and manually picked faults. The FauSIM index based on the Frechet distance compares
both the local and ´ global structures of faults. Experimental results show that the proposed
method has the capability to accurately detect faults in seismic sections, and the objective
FauSIM indices complied with the subjective observation of interpreters.

2.2 Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for

Image Denoising

In this paper, a deep convolutional neural network was proposed for image denoising, where
residual learning is adopted to separating noise from noisy observation. The batch
normalization and residual learning are integrated to speed up the training process as well as
boost the denoising performance. Unlike traditional discriminative models which train
specific models for certain noise levels, our single DnCNN model has the capacity to handle
the blind Gaussian denoising with unknown noise level. Moreover, we showed the feasibility
to train a single DnCNN model to handle three general image denoising tasks, including
Gaussian denoising with unknown noise level, single image super-resolution with multiple
upscaling factors, and JPEG image deblocking with different quality factors. Extensive
experimental results demonstrated that the proposed method not only produces favourable
image denoising performance quantitatively and qualitatively but also has promising run
time by GPU implementation. In future, we will investigate proper CNN models for denoising
of images

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 5

 COMPUTATIONAL IMAGING

with real complex noise and other general image restoration tasks.

2.3An Online Plug-and-Play Algorithm for Regularized Image

Reconstruction

The online PnP algorithm developed in this paper is beneficial in the context of large-scale
image reconstruction, when the amount of data is too large to be processed jointly. We have
presented an in-depth theoretical convergence analysis for both batch and online variants of
PnP-PGM. Our work represents a substantial extension of the current convergence theory of
PnP-algorithms for image reconstruction. Related experiments are also presented to
empirically confirm the proposed propositions and to elucidate the higher efficiency of
PnPSPGM in different representative situations. Future work will aim to apply the algorithm
to other image reconstruction tasks, relax some of the assumptions, and extend the theoretical
results in this paper to ADMM and APGM.

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 6

 COMPUTATIONAL IMAGING

CHAPTER-3
PHYSICS DRIVEN
IMAGING

3.1 ANALOG CAMERAS

In a film camera, lenses are used to bend the light and focus it onto a film substrate, as
depicted in Figure 3(a). Digital cam eras work largely the same way by simply placing a
digitizer at the film plane. In terms of (1)–(2) then, this example has an ideal linear model
with C = I so that the final image is really just the observation, assuming negligible noise.
Traditionally, the primary path to improving the image quality was through improvements to
the optical path itself, that is, through the use of better lenses that bring the physical sensing
process closer to the ideal identity C = I.

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 7

 COMPUTATIONAL IMAGING

3.2 X-RAY TOMOGRAPHY

X-ray tomography is used in applications such as non-destructive evaluation, security, and

medical imaging and is, in essence, an image of the attenuation produced by an object as
Xrays pass through it, as illustrated in Figure 3(b). The negative log ratio of the attenuated
output to the input incident energy is taken as the observation.

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 8

 COMPUTATIONAL IMAGING

where L is a given ray path. Mathematically, the observation (or projection), Y(L),is a line
integral of the desired attenuation image X(s) along the line L. The collection of all such
projections for all lines L (i.e., in every direction) defines what is called the Radon transform
of the image x. The Randon transform is a linear operation and, assuming no noise, can be
represented by (1), with C in this case being defined by the integral operator in (3). An
explicit analytic inverse of the Radon transform (i.e.,C -1) exists and forms the basis of the
imageformation method used by commercial scanners.

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 9

 COMPUTATIONAL IMAGING

This inversion approach, called the filtered back-projection (FBP) algorithm, is very efficient
in both computation and storage, requiring only simple filtering operations on the projections
followed by an accumulation process wherein these filtered projections are summed back
along their projection directions [4]; however, it assumes the existence of an infinite
continuum of projections, which is not possible in practice. Nevertheless, excellent
reconstructed images are possible if the sampling of y(L) is sufficiently dense. Thus, higher
quality images are obtained by making the X-ray machine better approximate the underlying

assumptions of the Radon transform inversion.

3.3 MRI

As depicted in Figure 3(c), MRI images the anatomy of the body through radio-frequency
excitation and strong magnetic fields—unlike X-ray imaging, no ionizing radiation is used.
Classical MRI acquisition is usually modelled as producing observations

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 10

 COMPUTATIONAL IMAGING

Y(f) are values of the desired image in the Fourier domain. The basic MRI ac quisition
acquires samples of these Fourier values line by line in the Fourier space, called the k-space,
and once sufficient Fourier samples are obtained, an image is produced by the application of
an inverse Fourier transform. As with X-ray tomography, the image formation follows from
an analytic formula for the inverse of the Fourier-based sensing operator such that improved
imagery is obtained through the denser and more complete sampling of the k-space [5]

3.4 SPOT-LIGHT MODE: SAR

Spotlight-mode SAR, as shown in Figure 3(d), is able to create high-resolution images of an

area day or night and in all types of weather and is thus widely used in remote sensing
applications. SAR works by transmitting microwave chirp pulses toward the ground and has a
resolution that is largely independent of the distance to the region of interest. SAR finds use
in mapping and monitoring vegetation and sea ice and in NASA planetary missions as well as
in military applications, just to name a few.

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 11

 COMPUTATIONAL IMAGING

the projection of the scattering field x(s) along the line L at angle i and range r such that (5) is
a 1D Fourier transform of the projection along the range direction. Thus, the observations for
SAR are again related to the values of the desired image x(s) in the Fourier domain, similar to
MRI. Combining (5) and (6), one can show that these observations are Fourier values of x(s)
on a polar grid; consequently, the standard image-formation algorithm for such SAR data is
the polar-format algorithm [6], which resamples the acquired polar Fourier data onto a
rectangular grid and then performs a standard inverse Fourier transform on the regirded data.

As in our other examples, the image-formation process follows from an analytic formula for
the inverse of the (Fourier-based) sensing operator, and improved imagery is obtained by
extending the support region of the acquired Fourier samples, which are related to both the
angular sector of SAR observation (related to the flight path of the sensor) as well as the
bandwidth of the transmitted microwave chirp. In all the examples that we have just
discussed, image formation comprises analytic inversion following from the physics of the
measurement operator [C in (1)]. These inversion approaches Operate on the observed data,
but the algorithms themselves are not dependent on the data; i.e., the structure of the
algorithm, along with any parameters, is fixed at the time of the algorithm design based
exclusively on the inversion of the measurement operator and is not learned from image data.
These examples of the early period of computational imaging can be characterized in our
taxonomy by (comparatively) low computation (e.g., Fourier transforms) and the presence of
“small-data” algorithms (i.e., just the observations). When data are complete and of high
quality and the system is designed to closely approximate the assumptions underlying the
inversion operators, these approaches can work very well. Yet, the physical systems are
constrained by the algorithmic assumptions on which the image formation is built, and if the
quality or quantity of observed data is reduced, much of the corresponding imagery can
exhibit confounding artifacts. An example would be standard medical tomography— since
the system will create an image using the FBP, the system needs to be such that a full 180° of
projections are obtained at a sufficient sampling density.

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 12

 COMPUTATIONAL IMAGING

CHAPTER-4
MBIR: THE RISE OF
COMPUTATIONAL
IMAGING
4.1 IMAGE FORMATION AS OPTIMIZATION

In general, in MBIR, the image-formation optimization problem can be taken to be of the

form

where x t is the resulting output image (an approximation to the true image); L is a loss
function that penalizes any discrepancy between the observed measurement y and its
prediction C(x) and R is a regularization term that penalizes solutions that are unlikely
according to prior knowledge of the solution space. This optimization is depicted
schematically in Figure 4.
Arguably, the simplest example of this formulation is Tikhonov regularization.

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 13

 COMPUTATIONAL IMAGING

where m is a parameter controlling the amount of regularization, and C is a problem-specific

operator [7], often chosen to be a derivative. This formulation also connects to probabilistic
models of the situation. In particular, the first term in (8) can be associated with a
loglikelihood, logp(y|x,C) and the second term with a log prior logp(x) under Gaussian
assumptions. With this association, (8) represents a maximum a posteriori (MAP) estimates of
the image given a likelihood and a prior, i.e.

There are a number of major advantages gained from the conceptual shift represented by
viewing image formation as the solution of (7). One advantage is that this view separates out
the components of the formulation from the algorithm used to solve it; i.e., the overall
problem is partitioned into independent modeling and optimization tasks. Indeed, there are
many approaches that can be used to solve (7), allowing discussion of the algorithm to be
decoupled from the debate about the problem formulation [although obviously some function
choices in
(7) correspond to easier problems, and thus, simpler algorithms].

Another advantage of this explicit focus on models is that one can consider a much richer set
of sensing operators since we are no longer limited to operators possessing simple, explicit,
and closed-form inverse formulations. For example, in X-ray tomography, the FBP algorithm
is an appropriate inversion operator only when a complete (uniform and densely sampled) set
of high-quality projection data is obtained—it is not an appropriate approach if data are
obtained, for example, over only a limited set of angles. On the other hand, the formulation
(7) is agnostic to such issues, requiring only that the C operator accurately captures the actual

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 14

 COMPUTATIONAL IMAGING

physics of acquisition. Thus, model-based inversion approaches have been success fully
applied in situations involving novel, nonstandard, and challenging imaging configurations
that could not have been considered previously. Furthermore, one can now consider the joint
design of sensing systems along with inversion, as occurs in computational photography.

A third advantage of model-based image formation is that (7) can be used to explicitly
account for noise or uncertainty in the data—the connection to statistical methods and MAP
estimation as alluded to previously [i.e., (9)] makes this connection obvious. For example,
rather than using a loss function corresponding to a quadratic penalty arising from Gaussian
statistics (as is common), one can consider instead a log-likelihood associated with Poisson-
counting statistics, which arises naturally in photon-based imaging. The use of such models
can provide superior noise reduction in low signal situations.

A final advantage of model-based inversion methods is the explicit use of prior-

imagebehavior information, as captured by the term R(x). We focus on the impact of prior
models next.

4.2 FOCUS ON PIRIOR MODELS

The growth of model-based methods led to a rich exploration of choices for the prior term
R(x) in (7). The simplest choice is perhaps a quadratic function of the unknown, x as
illustrated in (8). Such quadratic functions can be viewed as corresponding to a Gaussian
assumption on the statistics of C(x). Additionally, when applied to image derivatives, they
promote edge formation. In Table 1, we present a number of the nonquadratic penalty
functions that arose during this period, separated into those that are con vex and those that are
not. (The penalties tabulated in Table 1 are functions on scalars. To form R(x) these scalar
penalties could be applied element by element to, x=[x1,x2….xn] T Alternatively, referring to
(8), they could likewise be applied to elements of ( ).) x C In general, convex functions result
in easier optimization problems, while nonconvex functions possess more aggressive feature
preservation at the expense of more challenging solution computation. A key property that
these nonquadratic penalties promoted was the sparsity of the corresponding quantity. In
particular, when applied to x itself, the resulting solution becomes sparse, or when applied to
C(x) the quantity C(x) becomes sparse. A common example is to cast C as an approximation

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 15

 COMPUTATIONAL IMAGING

to the gradient operator such that the edge field then becomes sparse, resulting in piecewise
constant (mainly flat) solutions [16]. Eventually, interest nucleated around this concept of
sparsity and,
in particular, on the use of the 0 and 1, norms as choices in defining

One of the more visible applications of sparsity in model based reconstruction is compressed
sensing (CS) [18], [19]. In brief, under certain conditions, CS permits the recovery of signals
from their linear projections into a much lower dimensional space. That is, we recover x from
Y=Cx where x has length N, y has length M, and C is an M* N measurement matrix with the
subsampling rate (or sub rate) being S =M/N with . M<<N Because the number of
unknowns is much larger than the number of observations, recovering every x RN ! from its
corresponding y RM ! is impossible in general. The foundation of CS, however, is that, if x is
known to be sufficiently sparse in some domain, then exact recovery of x is possible. Such
sparsity can be with respect to some trans form T such that, when the transform is applied to
x, only K< M<< N coefficients in the set of transform coefficients X=Tx are nonzero.
Relating this situation back to (8), we can formulate the CS recovery problem as

with the final reconstruction being X=T -1 X. Ideally, for a T-domain sparse solution, we set
p=0 in (10), invoking the 0 , pseudo norm, which counts nonzero entries. Since this choice

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 16

 COMPUTATIONAL IMAGING

results in an NP-hard optimization, however, it is common to use, p 1 = there by applying a

convex relaxation of the 0 , problem. Interestingly, if the underlying solution is sufficiently
sparse, it can be shown that the two formulations yield the same final result [18], [19], [20].
Addition ally, for exact recovery, it is sufficient that the image transforms T and the
measurement matrix C be “mutually incoherent” in the sense that C cannot sparsely represent
the columns of the transform matrix T. Accordingly, an extensive number of images
transforms T have been explored; additionally, large-scale images can be re constructed by
applying the formulation in a block-by-block fashion (e.g., [21]). CS has garnered a great deal
of interest in the computational-imaging community in particular due to the demonstration of
devices (e.g., [22]) that conduct the compressed signal-sensing process Y=C(x) entirely
within optics, thereby acquiring the signal and reducing its dimensionality simultaneously
with little to no computation.

4.3 OPTIMIZATION ALGORITHMS

One of the challenges with MBIR-based approaches is that the resulting optimization
problems represented by (7) must be solved. Fortunately, solutions of such optimization
problems have been well studied, and a variety of methods exist, including the projected
gradient-descent algorithm, the Chambolle-Pock primal-dual algorithm, and the alternating
direction method of multipliers (ADMM) algorithm as well as others. These methods are, in
general, iterative algorithms composed of a sequence of steps that are repeated until a
stopping condition is reached. Of particular interest is the ADMM algorithm as well as other
similar methods exploit ing proximal operators [23], [24], [25]. Such methods split the
original problem into a series of pieces by way of associated proximal operators. Specifically,
the ADMM algorithm for solving (7) recasts (7) with an additional variable z and an equality
constraint

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 17

 COMPUTATIONAL IMAGING

where u is the scaled dual variable, and t is a penalty parameter. We have indicated previously
that (12) is a proximal operator, effectively performing smoothing or denoising to its
argument. We will return to this insight later as we consider the incorporation of learned
information into computational imaging.

Note that the ADMM algorithm comprises an image smoothing step (12), a data- or
observation integration step (13), and a simple reconciliation step (14). In the model-based
approach to image reconstruction discussed in this section, image formation is accomplished
through the solution of an optimization problem, and underlying models of acquisition and
image are made explicit.

The prior-image models can serve to stabilize situations with poor data, and conversely, the
observed data can compensate for overly simplistic prior image models. These MBIR
methods, including the use of nonquadratic models and the development of CS, have had a
profound impact on the computational-imaging field. They have allowed the coupled design
of sensing systems and inversion methods wherein sensor design can be integrated with
algorithm development in ways not previously possible. The impact has been felt in fields as
disparate as SAR, computed tomography, MRI, microscopy, and astronomical science. These
methods are characterized in our taxonomy by relatively high computation (resulting from the

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 18

 COMPUTATIONAL IMAGING

need to solve relatively large optimization problems iteratively) and the use of “small-data”
algorithms (again, just the observations).

CHAPTER -5
LEARNING BASED
FILTERS

5.1 ESTIMATE POST-PROCESSING

Perhaps the simplest way of folding deep learning into computational-imaging problems is to
apply a deep learning-based image enhancement as a post-processing step after a recon
structed image has been formed. In doing so, one uses an existing inversion scheme—such as
FBP for X-ray tomography or inverse Fourier transformation for MRI—to create an initial
reconstructed image. A deep network is then trained to bring that initial estimate closer to a
desired one by removing artifacts or noise. The enhancement can be done directly on the
formed image, or more recently, the deep enhancement network is trained on a set of residual
images between initial estimates and high-quality targets. Approaches in this vein are perhaps
the most straightforward way to include deep learning in image formation and were thus
some of the first methods developed. Example application domains include X-ray
tomography [29], [30] with subsampled and low-dose data as well as MRI [29], [31] with
subsampled Fourier data. Figure 5 illustrates this learning-driven post-processing approach

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 19

 COMPUTATIONAL IMAGING

for subsampled MRI along with a physics-driven explicit inversion as well as an MBIR-based
reconstruction

5.2 DATA PRE-PROCESSING

Another use of deep learning in computational imaging is as a preprocessing step. In these

methods, learning is used to “correct” imperfect, noisy, or incomplete data. Accordingly, data
can be made to more closely match the assumptions that underlie traditional physics-based
image-formation methods, which can then be used more effectively. Consequently, such an
approach can leverage existing conventional workflows and dedicated hardware. One
example can be found in X-ray tomography [32] wherein projection samples in the sinogram
domain that are missed due to the sparse angular sampling used to reduce dose are estimated
via a deep network; afterward, these corrected data are used in a conventional FBP algorithm.

5.3 LEARNED EXPLICIT PIRIORS

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 20

 COMPUTATIONAL IMAGING

Yet another use of deep learning in computational imaging has been to develop explicit
dataderived learned priors that can be used in an MBIR framework. An example of this
approach can be found in [33] wherein a K-sparse patch-based autoencoder is learned from
training images and then used as a prior in an MBIR reconstruction method. An autoencoder
(depicted in Figure 6) is a type of NN used to learn efficient reduced-dimensional coding’s (or
representations) of information and is composed of an encoder E and decoder D such that
D(E(x))~x with E(x) being of much lower dimension than x. The idea is that one is preserving
the “essence” of x in creating E(x) which can be considered a model for x and that, ideally,
D(E(x)) is removing only useless artifacts or noise. A sparsity-regularized autoencoder can be
obtained from a set of training data {xi}, as the solution of the optimization

where E and D are both NNs whose parameters are learned via solving (17). Once E and D of the
autoencoder are found, they can be used as a prior to reconstruct an image using an MBIR
formulation

Such an approach was adopted, for example, in [33], which ap plied (18) using a formulation
based on image patches, solving the resulting optimization via an alternating minimization.

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 21

 COMPUTATIONAL IMAGING

5.4 LEARNED INVERSE MAPPINGS

Deep learning can also be used to train a network that directly implements the inverse
mapping from the data y to estimate x t (e.g., [34]). That is, we learn a function F such that
x=F(y). This approach was taken in [35] with a method termed AUTOMAP. Four cases
motivated by tomography and MRI were considered: tomographic inversion, spiral k-space
MRI data, under sampled k-space MRI data, and misaligned k-space MRI data. The
AUTOMAP framework used a general feed-forward deep NN architecture composed of fully
connected layers followed by a sparse convolutional autoencoder. The network for each
application was learned from a set of corresponding training data without the inclusion of any

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 22

 COMPUTATIONAL IMAGING

physical or expert knowledge. Taking k-space MRI as an example, although we know that the
inverse Fourier transform produces the desired image, the AUTOMAP network has to
discover this fact directly from the training data alone. While the results are intriguing, the
approach suffers from the large number of training parameters required by the multiple fully
connected layers, which seems to limit its application to relatively small problems.

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 23

 COMPUTATIONAL IMAGING

CHAPTER-6
SPS INVOLMENT
SPS INVOLMENT

This section provides a brief history of SPS initiatives and activities related to computational
imaging, including the establishment of IEEE Transactions on Computational Imaging (TCI)
and the SPS Computational Imaging Technical Committee (CI TC) as well as support for
community-wide conference and seminar activities.

TCI

TCI Motivated by the rapid growth of computational imaging as a research and technology
area distinct from image processing, the creation of a new journal on computational imaging
was first proposed to the SPS Technical Activities Board Periodicals Committee in 2013 in an
effort led by three serving and prior editors-in-chief of IEEE Transactions on Image
Processing: Charles Bouman, Thasos Pappas, and Clem Karl. The motivation for the new
journal was the rapid growth of computational imaging as a research and technology area
distinct from image processing. The journal was launched in 2015, with Clem Karl as its
inaugural editor-in-chief. TCI focuses on solutions to imaging problems in which
computation plays an integral role in the formation of an image from sensor data. The
journal’s scope includes all areas of computational imaging, ranging from theoretical
foundations and methods to innovative computational-imaging system design. Topics of
interest include advanced algorithms and mathematical methodology, model-based data

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 24

 COMPUTATIONAL IMAGING

inversion, methods for image recovery from sparse and incomplete data, techniques for
nontraditional sensing of image data, methods for dynamic information acquisition and
extraction from imaging sensors, and software and hardware for efficient computation in
imaging systems. TCI has grown rapidly since its inception. With around 40 submissions a
month and an impact factor of 4.7, it is now one of the leading venues for the publication of
computational imaging research. TCI is somewhat unique within the SPS publications
portfolio in that it draws submissions from a broad range of professional communities beyond
the SPS, including SIAM, Optica (formerly the Optical Society of America), and SPIE, and
that it has connections to a broad range of domains, including radar sensing, X-ray imaging,
optical microscopy, and ultrasound sensing. The editorial board similarly includes members
from these diverse communities.

CI TC

The Computational Imaging Special Interest Group was established within the SPS in 2015
and was promoted to TC status in 2018. The goal of the CI TC is the promotion of compu
tational imaging as well as the formation of a community of computational-imaging
researchers that crosses the traditional boundaries of professional-society affiliations and
academic disciplines, with activities including the sponsorship of workshops and special
sessions, assistance with the review of papers submitted to the major society conferences, and
the sup port and promotion of TCI. The CI TC currently consists of the chair, the vice chair
(or the past chair), and 40 regular voting members. Additionally, there are nonvoting advisory
members, associate members, and affiliate members. To promote collaboration across
communities, the CI TC also appoints liaisons to other IEEE and non-IEEE professional
groups whose interests intersect with computational imaging.

Those interested in becoming involved with the CI TC can become an affiliate member via an
easy web-based registration process (see https://signalprocessingsociety.org/community
involvement/computational-imaging/affiliates). Affiliates are nonelected nonvoting members
of the TC, and affiliate membership is open to IEEE Members of all grades as well as to
members of certain other professional organizations in inter disciplinary fields within the CI
TC’s scope

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 25

 COMPUTATIONAL IMAGING

6.1 ADVANTAGES AND DISADVANTAGES

ADVANTAGES:

➢ CI permits better or previously impossible images for machine vision systems to be

created at lower cost
➢ CI with its targeted feature extraction, directly outputs the image your vision
algorithm needs.
➢ Allows you to shorten development time and create superior machine vision
solutions
➢ CI allows you to get the image you need , in a very efficient way.

DISADVANTAGES:

➢ Increases noise
➢ Reduces dynamic range
➢ Long distance imaging is difficult
➢ Immature technology
➢ Data processing pressure is high

6.2 APPLICATIONS

APPLICATIONS:

➢ Total internal reflection

➢ Spatial light modulators
➢ Synthetic aperture radar
➢ Near field scanning optical microscopy
➢ Imaging systems

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 26

 COMPUTATIONAL IMAGING

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 27

 COMPUTATIONAL IMAGING

CHAPTER-7
CONCLUSION

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 28

 COMPUTATIONAL IMAGING

7.1 CONCLUSION

In conclusion, computational imaging has emerged as a significant and distinct area of

research. With the increasing demand for improved information extraction from existing
imaging sys terms coupled with the growth of novel imaging applications and sensing
configurations, researchers have turned to advanced computational and algorithmic
techniques. These techniques, including deep learning methods, have led to the development
of new imaging modalities as well as the ability to process and analyse large datasets. The
SPS has played an important role in this growing area through the creation of a new highly
ranked journal, a new energetic TC, and support for new cross-society conference and
seminar activities. The continued advancement of computational imaging will impact a wide
range of applications,
from health care to science to defence and beyond

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 29

 COMPUTATIONAL IMAGING

7.2 REFERENCES

[1] Z. Wang and G. AlRegib, “Interactive fault extraction in 3-D seismic data using the Hough
transform and tracking vectors,” IEEE Trans. Comput. Imag., vol. 3, no. 1, pp. 99–109, Mar. 2017,
doi:
10.1109/TCI.2016.2626998.

[2] L. Tian, X. Li, K. Ramchandran, and L. Waller, “Multiplexed coded illumina tion for Fourier
Ptychography with an LED array microscope,” Biomed. Opt. Exp., vol. 5, no. 7, pp. 2376–2389,
Jul. 2014, doi: 10.1364/BOE.5.002376.

[3] K. L. Bouman, “Portrait of a black hole: Here’s how the event horizon telescope team pieced
together a now-famous image,” IEEE Spectr., vol. 57, no. 2, pp. 22–29, Feb. 2020, doi:
10.1109/MSPEC.2020.8976898.

[4] L. A. Shepp and B. F. Logan, “The Fourier reconstruction of a head section,” IEEE Trans. Nucl. Sci.,
vol. 21, no. 3, pp. 21–43, Jun. 1974, doi: 10.1109/ TNS.1974.6499235. [Online]. Available:
http://ieeexplore.ieee.org/document/ 6499235/

[5] Z.-P. Liang and P. C. Lauterbur, Principles of Magnetic Resonance Imaging: A Signal Processing
Perspective. New York, NY, USA: IEEE Press, 2000.

[6] C. V. Jakowatz, D. E. Wahl, P. A. Thompson, P. H. Eichel, and D. C. Ghiglia, Spotlight-Mode

Synthetic Aperture Radar: A Signal Processing Approach. New York, NY, USA: Springer, 1996.

[7] M. Vauhkonen, D. Vadasz, P. Karjalainen, E. Somersalo, and J. Kaipio, “Tikhonov regularization

and prior information in electrical impedance tomogra phy,” IEEE Trans. Med. Imag., vol. 17, no.
2, pp. 285– 293, Apr. 1998, doi: 10.1109/42.700740. [Online]. Available:
http://ieeexplore.ieee.org/document/ 700740/

[8] J. Besag, “Digital image processing: Towards Bayesian image analysis,” J. Appl. Statist., vol. 16,
no.
3, pp. 395–407, Jan. 1989, doi: 10.1080/02664768900000049.

[9] S. Geman and D. E. McClure, “Statistical methods for tomographic image reconstruction,” in
Proc.
46th Session Int. Statist. Inst., 1987, vol. 52, pp. 5–21.

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 30

 COMPUTATIONAL IMAGING

[10] P. Charbonnier, L. Blanc-Feraud, G. Aubert, and M. Barlaud, “Deterministic edge-preserving

regularization in computed imaging,” IEEE Trans. Image Process., vol. 6, no. 2, pp. 298–311, Feb.
1997, doi: 10.1109/83.551699. [Online]. Available:
https://ieeexplore.ieee.org/document/551699/

[11] P. Green, “Bayesian reconstructions from emission tomography data using a modified EM
algorithm,” IEEE Trans. Med. Imag., vol. 9, no. 1, pp. 84–93, Mar. 1990, doi: 10.1109/42.52985.
[Online]. Available: http://ieeexplore.ieee.org/ document/52985/

[12] A. Blake, “Comparison of the efficiency of deterministic and stochastic algo rithms for visual
reconstruction,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 11, no. 1, pp. 2–12, Jan. 1989, doi:
10.1109/34.23109. [Online]. Available: http://ieeex plore.ieee.org/document/23109/

[13] P. J. Huber, “Robust estimation of a location parameter,” Ann. Math. Statist., vol. 35, no. 1, pp.
73–
101, Mar. 1964, doi: 10.1214/aoms/1177703732. [Online]. Available:
http://projecteuclid.org/euclid.aoms/1177703732

[14] T. Hebert and R. Leahy, “A generalized EM algorithm for 3-D Bayesian recon struction from
Poisson data using Gibbs priors,” IEEE Trans. Med. Imag., vol. 8, no. 2, pp. 194–202, Jun. 1989,
doi:
10.1109/42.24868. [Online]. Available: http:// ieeexplore.ieee.org/document/24868/

[15] D. Geman and G. Reynolds, “Constrained restoration and the recovery of dis continuities,” IEEE
Trans. Pattern Anal. Mach. Intell., vol. 14, no. 3, pp. 367–383, Mar. 1992, doi: 10.1109/34.120331.
[Online]. Available: http://ieeexplore.ieee.org/ document/120331/

[16] C. Bouman and K. Sauer, “A generalized Gaussian image model for edge- preserving MAP
estimation,” IEEE Trans. Image Process., vol. 2, no. 3, pp. 296 310, Jul. 1993, doi:
10.1109/83.236536. [Online]. Available: http://ieeexplore.ieee. org/document/236536/

[17] J. Mairal, “Sparse modeling for image and vision processing,” Found. Trends® Comput. Graphics
Vision, vol. 8, nos. 2–3, pp. 85–283, Dec. 2014, doi: 10.1561/ 0600000058. [Online]. Available:
http://www.nowpublishers.com/articles/foundations -and-trends-in-computer-graphics-
andvision/CGV-058

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 31

 COMPUTATIONAL IMAGING

[18] D. Donoho, “Compressed sensing,” IEEE Trans. Inf. Theory, vol. 52, no. 4, pp. 1289–1306, Apr.
2006, doi: 10.1109/TIT.2006.871582. [Online]. Available: http://
ieeexplore.ieee.org/document/1614066/ [19] E. Candès, J. Romberg, and T. Tao, “Robust
uncertainty principles: Exact sig nal reconstruction from highly incomplete frequency
information,” IEEE Trans. Inf. Theory, vol. 52, no. 2, pp. 489–509, Feb.
2006, doi: 10.1109/TIT.2005.862083. [Online]. Available:
http://ieeexplore.ieee.org/document/1580791/

[20] D. Malioutov, M. Cetin, and A. Willsky, “Optimal sparse representations in general overcomplete
bases,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., Montreal, QC, Canada: IEEE,
2004, vol. 2, pp. ii–793-6, doi: 10.1109/ ICASSP.2004.1326377.

[21] S. Mun and J. E. Fowler, “Block compressed sensing of images using direction al transforms,” in
Proc. IEEE Int. Conf. Image Process., Cairo, Egypt, Nov. 2009, pp. 3021–3024, doi:
10.1109/ICIP.2009.5414429.

[22] D. Takhar, J. N. Laska, M. B. Wakin, M. F. Duarte, D. Baron, S. Sarvotham, K. F. Kelly, and R. G.

Baraniuk, “A new compressive imaging camera architecture using optical-domain compression,”
in Proc. Comput. Imag. IV (SPIE), San Jose, CA, USA, Jan. 2006, p. 606509, doi:
10.1117/12.659602.

[23] S. Boyd, N. Parikh, E. Chu, B. Peleato, and J. Eckstein, “Distributed optimiza tion and statistical
learning via the alternating direction method of multipliers,” Found. Trends® Mach. Learn., vol.
3, no.
1, pp. 1–122, Jul. 2011, doi: 10.1561/2200000016. [Online]. Available:
https://www.nowpublishers.com/article/ Details/MAL-016

[24] N. Parikh and S. Boyd, “Proximal algorithms,” Found. Trends Optim., vol. 1, no. 3, pp. 127–239,
Jan. 2014, doi: 10.1561/2400000003.

[25] P. L. Combettes and J.-C. Pesquet, “Proximal splitting methods in signal pro cessing,” in Proc.
FixedPoint Algorithms Inverse Probl. Sci. Eng., H. H. Bauschke, R. S. Burachik, P. L. Combettes, V.
Elser, D. R. Luke, and H. Wolkowicz, Eds. New York, NY, USA: Springer, 2011, vol. 49, pp. 185–212.

[26] B. A. Olshausen and D. J. Field, “Emergence of simple-cell receptive field properties by learning a
sparse code for natural images,” Nature, vol. 381, no. 6583, pp. 607–609, Jun. 1996, doi:
10.1038/381607a0. [Online]. Available: http://www. nature.com/articles/381607a0

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 32

 COMPUTATIONAL IMAGING

[27] M. Elad and M. Aharon, “Image denoising via sparse and redundant represen tations over
learned dictionaries,” IEEE Trans. Image Process., vol. 15, no. 12, pp. 3736–3745, Dec. 2006, doi:
10.1109/TIP.2006.881969. [Online]. Available: http:// ieeexplore.ieee.org/document/4011956/

[28] J. Adler and O. Oktem, “Learned primal-dual reconstruction,” IEEE Trans. Med. Imag., vol. 37, no.
6, pp. 1322–1332, Jun. 2018, doi: 10.1109/TMI.2018.2799231. [Online]. Available:
https://ieeexplore.ieee.org/document/8271999/

[29] K. H. Jin, M. T. McCann, E. Froustey, and M. Unser, “Deep convolutional neural network for
inverse problems in imaging,” IEEE Trans. Image Process., vol. 26, no. 9, pp. 4509–4522, Sep.
2017, doi: 10.1109/TIP.2017.2713099. [Online]. Available:
http://ieeexplore.ieee.org/document/7949028/

[30] C. You et al., “Structurally-sensitive multi-scale deep neural network for low dose CT denoising,”
IEEE Access, vol. 6, pp. 41,839–41,855, Jul. 2018, doi: 10.1109/ACCESS.2018.2858196.

[31] G. Yang et al., “DAGAN: Deep de-aliasing generative adversarial networks for fast compressed
sensing MRI reconstruction,” IEEE Trans. Med. Imag., vol. 37, no. 6, pp. 1310–1321, Jun. 2018,
doi: 10.1109/TMI.2017.2785879. [Online]. Available:
https://ieeexplore.ieee.org/document/8233175/

[32] M. U. Ghani and W. C. Karl, “Deep learning-based sinogram completion for low-dose CT,” in Proc.
IEEE 13th Image, Video, Multidimensional Signal Process. Workshop (IVMSP), Zagorochoria, Greece:
IEEE, Jun. 2018, pp. 1–5, doi: 10.1109/IVMSPW.2018.8448403.

[33] D. Wu, K. Kim, G. El Fakhri, and Q. Li, “Iterative low-dose CT reconstruction with priors trained by
artificial neural network,” IEEE Trans. Med. Imag., vol. 36, no. 12, pp. 2479–2486, Dec. 2017, doi:
10.1109/TMI.2017.2753138. [Online]. Available:
https://ieeexplore.ieee.org/document/8038851/

[34] Y. Wu and Y. Lin, “InversionNet: An efficient and accurate data-driven full waveform inversion,”
IEEE Trans. Comput. Imag., vol. 6, pp. 419–433, 2020, doi: 10.1109/TCI.2019.2956866. [Online].
Available: https://ieeexplore.ieee.org /document/8918045

[35] B. Zhu, J. Z. Liu, S. F. Cauley, B. R. Rosen, and M. S. Rosen, “Image recon struction by
domaintransform manifold learning,” Nature, vol. 555, no. 7697, pp. 487–492, Mar. 2018, doi:
10.1038/nature25988. [Online]. Available: http://www. nature.com/articles/nature25988

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 33

 COMPUTATIONAL IMAGING

[36] D. Ulyanov, A. Vedaldi, and V. Lempitsky, “Deep image prior,” Int. J. Comput. Vision, vol. 128, pp.
1867–1888, Jul. 2020, doi: 10.1007/s11263 020-01303-4.

[37] T. Würfl, F. C. Ghesu, V. Christlein, and A. Maier, “Deep learning comput ed tomography,” in Proc.
Med. Image Comput. Comput.-Assisted Intervention (MICCAI), S. Ourselin, L. Joskowicz, M. R.
Sabuncu, G. Unal, and W. Wells, Eds. Cham, Switzerland: Springer International Publishing, 2016,
vol. 9902, pp. 432–440.

[38] D. H. Ye, G. T. Buzzard, M. Ruby, and C. A. Bouman, “Deep back projection for sparse-view CT
reconstruction,” in Proc. IEEE Global Conf. Signal Inf. Process. (GlobalSIP), Anaheim, CA, USA:
IEEE, Nov. 2018, pp. 1–5, doi: 10.1109/ GlobalSIP.2018.8646669.

[39] S. V. Venkatakrishnan, C. A. Bouman, and B. Wohlberg, “Plug-and-play pri ors for model based
reconstruction,” in Proc. IEEE Global Conf. Signal Inf. Process., Dec. 2013, pp. 945–948, doi:
10.1109/GlobalSIP.2013.6737048.

[40] S. Sreehari, S. V. Venkatakrishnan, B. Wohlberg, G. T. Buzzard, L. F. Drummy, J. P. Simmons, and C.

A. Bouman, “Plug-and-play priors for bright field electron tomography and sparse interpolation,”
IEEE
Trans. Comput. Imag., vol. 2, no. 4, pp. 408–423, Dec. 2016, doi: 10.1109/TCI.2016.2599778. [Online].
Available: http://ieeexplore.ieee.org/document/7542195/

[41] A. Buades, B. Coll, and J.-M. Morel, “Non-local means denoising,” IPOL J. Image Process. On Line,
vol. 1, pp. 208–212, Sep. 2011, doi: 10.5201/ipol.2011. bcm_nlm. [Online]. Available:
https://www.ipol.im/pub/art/2011/bcm_nlm/?utm _source=doi

[42] K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, “Image restoration by sparse 3D

transformdomain collaborative filtering,” in Proc. Image Process., Algorithms Syst. VI, J. T. Astola,
K. O. Egiazarian, and E. R. Dougherty, Eds. San Jose, CA, USA, Feb. 2008, p. 681207.

[43] K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: Residual
learning of deep CNN for image denoising,” IEEE Trans. Image Process., vol. 26, no. 7, pp. 3142–
3155, Jul. 2017, doi: 10.1109/TIP.2017.2662206. [Online]. Available:
https://ieeexplore.ieee.org/document/7839189/

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 34

 COMPUTATIONAL IMAGING

[44] U. S. Kamilov, H. Mansour, and B. Wohlberg, “A plug-and-play priors approach for solving
nonlinear imaging inverse problems,” IEEE Signal Process. Lett., vol. 24, no. 12, pp. 1872–1876,
Dec. 2017, doi:
10.1109/LSP.2017.2763583. [Online]. Available: http://ieeexplore.ieee.org/document/8068267/

[45] Y. Sun, B. Wohlberg, and U. S. Kamilov, “An online plug-and-play algorithm for regularized image
reconstruction,” IEEE Trans. Comput. Imag., vol. 5, no. 3, pp. 395–408, Sep. 2019, doi:
10.1109/TCI.2019.2893568.

[46] Y. Romano, M. Elad, and P. Milanfar, “The little engine that could: Regularization by denoising
(RED),” SIAM J. Imag. Sci., vol. 10, no. 4, pp. 1804 1844, Jan. 2017, doi: 10.1137/16M1102884.

[47] E. T. Reehorst and P. Schniter, “Regularization by denoising: Clarifications and new

interpretations,” IEEE Trans. Comput. Imag., vol. 5, no. 1, pp. 52–67, Mar. 2019, doi:
10.1109/TCI.2018.2880326.
[Online]. Available: https://ieeexplore.ieee. org/document/8528509/

[48] G. T. Buzzard, S. H. Chan, S. Sreehari, and C. A. Bouman, “Plug-and-play unplugged:

Optimizationfree reconstruction using consensus equilibrium,” SIAM J. Imag. Sci., vol. 11, no. 3,
pp. 2001–2020, Jan. 2018, doi: 10.1137/ 17M1122451.

[49] M. U. Ghani and W. C. Karl, “Data and image prior integration for image reconstruction using
consensus equilibrium,” IEEE Trans. Comput. Imag., vol. 7, pp. 297–308, Mar. 2021, doi:
10.1109/TCI.2021.3062986. [Online]. Available:
https://ieeexplore.ieee.org/document/9366922/

[50] V. Monga, Y. Li, and Y. C. Eldar, “Algorithm unrolling: Interpretable, efficient deep learning for
signal and image processing,” IEEE Signal Process. Mag., vol. 38, no. 2, pp. 18–44, Mar. 2021, doi:
10.1109/MSP.2020.3016905. [Online]. Available: https://ieeexplore.ieee.org/document/9363511/

[51] K. Gregor and Y. LeCun, “Learning fast approximations of sparse coding,” in Proc. 27th Int. Conf.
Mach. Learn., Haifa, Israel: Omnipress, Jun. 2010, pp. 399–406.

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 35

 COMPUTATIONAL IMAGING

[52] H. Gupta, K. H. Jin, H. Q. Nguyen, M. T. McCann, and M. Unser, “CNN based projected gradient
descent for consistent CT image reconstruction,” IEEE Trans. Med. Imag., vol. 37, no. 6, pp.
1440–1453,
Jun. 2018, doi: 10.1109/ TMI.2018.2832656. [Online]. Available:
https://ieeexplore.ieee.org/document/ 8353870/

[53] Y. Li, M. Tofighi, V. Monga, and Y. C. Eldar, “An algorithm unrolling approach to deep image
deblurring,” in Proc. IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP), Brighton, U.K.: IEEE,
May 2019, pp. 7675–7679, doi: 10.1109/ICASSP.2019.8682542.

[54] S. Lunz, O. Öktem, and C.-B. Schönlieb, “Adversarial regularizers in inverse problems,” in Proc.
32nd Int. Conf. Neural Inf. Process. Syst., Red Hook, NY, USA: Curran Associates, Inc., Dec. 2018,
pp. 8516– 8525.

[55] H. Sun and K. L. Bouman, “Deep probabilistic imaging: Uncertainty quantifi cation and multi-
modal solution characterization for computational imaging,” in Proc. AAAI Conf. Artif. Intell., May
2021, vol.
35, no. 3, pp. 2628–2637, doi: 10.1609/aaai.v35i3.16366. [Online]. Available:
https://ojs.aaai.org/index.php/ AAAI/article/view/16366

[56] Y. Song, L. Shen, L. Xing, and S. Ermon, “Solving inverse problems in medi cal imaging with
scorebased generative models,” in Proc. Int. Conf. Learn. Representations, Mar. 2022. [Online].
Available:
https://openreview.net/ forum?id=vaRCHVj0Ugi

[57] H. Chung and J. C. Ye, “Score-based diffusion models for accelerated MRI,” Med. Image Anal.,
vol. 80, Aug. 2022, Art. no. 102479, doi: 10.1016/j. media.2022.102479. [Online]. Available:
https://linkinghub.elsevier.com/retrieve/ pii/S1361841522001268

[58] C. Ekmekci and M. Cetin, “Uncertainty quantification for deep unrolling-based computational
imaging,” IEEE Trans. Comput. Imag., vol. 8, pp. 1195–1209, Dec. 2022, doi:
10.1109/TCI.2022.3233185.

[59] J. Lehtinen, J. Munkberg, J. Hasselgren, S. Laine, T. Karras, M. Aittala, and T. Aila, “Noise2Noise:
Learning image restoration without clean data,” in Proc. 35th Int. Conf. Mach. Learn., PMLR, Jul.
2018, pp. 2965–2974. [Online]. Available: https://proceedings.mlr.press/v80/lehtinen18a.html

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 36

 COMPUTATIONAL IMAGING

[60] J. Liu, Y. Sun, C. Eldeniz, W. Gan, H. An, and U. S. Kamilov, “RARE: Image reconstruction using
deep priors learned without groundtruth,” IEEE J. Sel. Topics Signal Process., vol. 14, no. 6, pp.
1088–1099,
Oct. 2020, doi: 10.1109/ JSTSP.2020.2998402. [Online]. Available:

https://ieeexplore.ieee.org/document/ 9103213

DEPARTMENT OF ECE CMR COLLEGE OF ENGINEERING AND TECHNOLOGY 37