introduction to image super-resolution - department of computer
TRANSCRIPT
References
1. S.C. Park, M.K. Park, and M.G. KANG, “Super-Resolution Image Reconstruction: A Technical Overview”, IEEE Signal Processing Magazine, Vol. 20, pp. 21-36, May 2003
2. W.T. Freeman, T.R. Jones, and E.C. Pasztor, “Example-Based Super-Resolution”, IEEE Computer Graphics and Applications, Vol. 22, pp. 56-65, 2002.
Overview
• Introduction• Super-resolution Techniques
– Multi-frame Super-resolution– Single-frame Super-resolution
• Conclusion
Terminology
• Low-Resolution (LR):– Pixel density within an image is small, therefore
offering less details.• High-Resolution (HR):
– Pixel density within an image is larger, therefore offering more details.
• Superresolution (SR):– Obtaining a HR image from one or multiple LR
images .
Application
• Medical imaging (ie. CAT, MRI, etc).• Satellite imaging• Enlarging consumer photographs• Video surveillance (ie. Car wash
kidnapping).• Converting NTSC video content to high-
definition television
How to increase resolution?
• Possible ways for increasing an image resolution:
– Reducing pixel size.– Increase the chip-size.– Super-resolution.
How to increase resolution?
• Reduce pixel size:– Increase the number of pixels per unit
area.– Advantage:
• Increases spatial resolution.– Disadvantage:
• Noise introduced.• As the pixel size decreases, the amount of
light decreases.
How to increase resolution?
• Increase the chip size (HW):
– Advantage:• Enhances spatial resolution.
– Disadvantage:• High cost for high precision optics.
How to increase resolution?
• Superresolution (SR):– Process of combining multiple low
resolution images to form a high resolution image.
– Advantages:• Cost less than comparable approaches.• LR imaging systems can still be utilized.
Overview
• Introduction• Super-resolution Techniques
– Multi-frame Super-resolution– Single-frame Super-resolution
• Conclusion
Multi-frame Super-resolution • How can we obtain a HR image from multiple
LR images?– Basic premise is the availability of multiple LR
image captured form the same scene.– These multiple LR images provide different “looks”
at the same scene. – Each LR is naturally shifted with subpixel precision.– If LR images are shifted by integer units, then each
image contains the same information, SR is not possible.
– If LR images have different subpixel shifts, then SR is possible.
Observation ModelFirst step to understanding SR is to formulate an Observation Model to relate the LR images to the desired HR image.
• Desired HR image:– Size:– Vector: where
• LR images:– Size: – K-th LR image:
where
Observation Model
2211 NLNLN ×=2211 NLNL ×
Tk,Mk,2k,1 ,....,y,yy ][yk =
21 NN ×
TNxxxx ],....,,[ 21=
21...,21 NNMandp,,k ×==
• Observation model can be represented as follows:
– is a warp matrix– represents blur matrix– is a sub-sampling matrix– represents noise matrix
• Without loss of generality, it can also be represented as follows:
Observation Model
DkBkM
pkfornxMDB kkk ≤≤+= 1yk
pkfornxW kk ≤≤+= 1yk
kn
Nonuniform interpolation approach
• Registration:– Need to estimate the scene motion for each image
with reference to one particular image.– The motion can be estimated as a 1-to-1
representation between the reference image and each of the images.
Nonuniform interpolation approach
• Registration:– Estimating the completely arbitrary motion in
real world image scenes is extremely difficult, with almost no guarantees of estimator performance.
– Incorrect estimates of motion have disastrous implications on overall SR performance.
Nonuniform interpolation approach
• Interpolation:– Since the shifts between the LR images are
arbitrary, the images will not always match up to a uniformly to the HR grid.
– Thus, nonuniform interpolation is necessary to obtain a uniformly spaced HR image from a nonuniformly spaced composite of LR images.
– Nonuniform interpolation between LR images are used to improve resolution.
Nonuniform interpolation approach
• Interpolation:– This step requires interpolation when the estimated
fractional unit of motion is not equal to the HR grid reference image.
Nonuniform interpolation approach
• Deblurring:– In SR, blur is usually modeled as a spatial
averaging operator as shown below.
Regularized SR Reconstruction
• If there are enough LR images, we can solve
• In reality, it is hard to find sufficient number of LR images. Use procedure (called regularization) to stabilize the inversion of ill-posed problem.
– Deterministic Approach (CLS)
– Stochastic Approach (MAP)
pkfornxW kk ≤≤+= 1yk
Deterministic Approach (CLS)• CLS can be formulated by choosing x to
minimize the Lagrangian
– C is generally a high-pass filter– α is regularization parameter
• The cost function above is convex and differentiable with the use of a quadratic regularization term. We can find a unique estimate image using iterative techniques
⎥⎦
⎤⎢⎣
⎡+−∑
=
p
kkk CxxWy
1
2 α
x̂k
p
k
Tk
p
k
Tk
Tk yWxCCWW ∑∑
==
=⎥⎦
⎤⎢⎣
⎡+
11
ˆα
Stochastic Approach (MAP)
• Bayesian approach provides a flexible and convenient way to model a priori knowledge concerning solution
• Using MRF Gibbs priori to define P(x)
).,...,,|(maxarg 21 pyyyxPx =
)}.(ln)|,...,,(max{lnarg 21 xPxyyyPx p +=
∑∈
−=−==Sc
c xZ
xUZ
xXP ))(exp(1)}(exp{1)( ϕ
Other Approaches
• Frequency Domain Approach• Projection onto Convex Sets Approach• ML (maximum likelihood approach)• ML-POCS hybrid approach• Iterative back-projection approach• Adaptive Filtering Approach• Motionless SR Reconstruction
Approach
Overview
• Introduction• Super-resolution Techniques
– Multi-frame Super-resolution– Single-frame Super-resolution
• Conclusion
Overview
• Introduction• Super-resolution Techniques
– Multi-frame Super-resolution– Single-frame Super-resolution
• Conclusion
Single-frame SR• Traditional resolution enhancement:
– Smoothing (Gaussian, Wiener, and median filters)– Interpolation (Nearest ngbr, bilinear, bicubic and
cubic spline etc)– Sharpening by amplifying existing image details
(it is useful to do, provided noise isn’t amplified)• Single-frame SR:
– Estimate missing high-resolution detail that isn’t present in the original image, and which we can’t make visible by simple sharpening
Example-based SR
• Algorithm uses a training set to learn the fine details of an image at low-resolution.
• It then uses those learned relationships to predict fine details in other images.– Markov network– One pass algorithm
Training Set Generation• Start with a collection of HR images.• For each HR image, degrade it to get a LR
image.– Blur & subsample each to create LR image of ¼ total
pixels.• Apply analytical interpolation to the LR image.
– ie. Cubic spline.– This will generate an image of desired # of pixels, but
lacking the HR detail.• Band pass filter and contrast normalize the
interpolated image AND the original HR image.
Markov network
• Select the 16 or so closet examples to each input patch as the different states of the hidden nodes, x, that we seek to estimate.
• Maximize
where
, the sum of squared differences between patch candidates xi and xjin their overlap regions at nodes i and j
∏ ∏=)(
),(),(1)|(ij k
kkkjiij yxxxZ
yxP φψ
⎥⎦
⎤⎢⎣
⎡−= 22
),(exp),(
σψ jiij
jiij
xxdxx
),( jiij xxd
Conclusions and future works
• Current SR approaches are effective to some extent
• SR considering registration error: – Use total least squares method to minimize the error– Use channel adaptive regularization: SR images with
large registration error should be less contributed to the estimate of the HR.
• Blind SR Image Reconstruction: when blurring process is unknown. Need blur identification.
• Computationally efficient SR Algorithm