Title: Discriminative Approach for Transform Based Image Restoration
1Discriminative Approach forTransform Based
Image Restoration
SIAM Imaging Science, July 2008
- Yacov Hel-Or Doron Shaked Gil
Ben-Artzi -
The Interdisciplinary Center Israel
Bar-Ilan Univ. Israel
HP Las
2Motivation Image denoising
- Can we clean Lena?
3Broader Scope
- Inpainting
- De-blurring
- De-noising
- De-mosaicing
- All the above deal with degraded images.
- Their reconstruction requires solving an
- inverse problem
4Key point Stat. Prior of Natural Images
likelihood
prior
Bayesian estimation
5Problem P(x) is complicated to model
- Defined over a huge dimensional space.
- Sparsely sampled.
- Known to be non Gaussian.
A prior p.d.f. of a 2x2 image patch
form Mumford Huang, 2000
6The Wavelet Transform Marginalizes Image Prior
- Observation1 The Wavelet transform tends to
de-correlate pixel dependencies of natural images.
W.T.
7- Observation2 The statistics of natural images
are homogeneous.
Share the same statistics
8Donoho Johnston 94 Wavelet Shrinkage
Denoising Unitary Case
- Degradation Model
- MAP estimation in the transform domain
9- The Wavelet domain diagonalizes the system.
- The estimation of a coefficient depends
solely on its own measured value - This leads to a very useful property
- Modify coefficients via scalar mapping
functions -
where Bk stands for the kth band
10Shrinkage Pipe-line
BT1
BT1
B1
B3
y
B3
B1
BT2
BT2
B2
BT3
BT3
B2
y
?k(Bky)
BTk?k(Bky)
Bky
Image domain
Transform domain
Image domain
Result
11Wavelet Shrinkage as aLocally Adaptive Patch
Based Method
KxK
12- Can be viewed as shrinkage de-noising in a
Unitary Transform (Windowed DCT).
KxK bands
WDCT
Unitary Transform
xiB
WDCT-1
yiB
13Alternative Approach Sliding Window
KxK
14- Can be viewed as shrinkage de-noising in a
redundant transform (U.D. Windowed DCT).
UWDCT
Redundant Transform
xiB
UWDCT-1
yiB
15How to Design the Mapping Functions?
- Descriptive approach The shape of the mapping
function ?j depends solely on Pj and the noise
variance ?.
noise variance (?)
Modeling marginal p.d.f. of band j
MAP objective
yw
16- Commonly Pj(yB) are approximated by GGD
for plt1
from Simoncelli 99
17Hard Thresholding
Soft Thresholding
Linear Wiener Filtering
MAP estimators for GGD model with three different
exponents. The noise is additive Gaussian, with
variance one third that of the signal.
from Simoncelli 99
18- Due to its simplicity Wavelet Shrinkage became
extremely popular - Thousands of applications.
- Thousands of related papers
- What about efficiency?
- Denoising performance of the original Wavelet
Shrinkage technique is far from the
state-of-the-art results. - Why?
- Wavelet coefficients are not really independent.
19Recent Developments
- Since the original approach suggested by DJ
significant improvements were achieved
Original Shrinkage
Redundant Representation
Joint (Local) Coefficient Modeling
- Overcomplete transform
- Scalar MFs
- Simple
- Not considered state-of-the-art
- Multivariate MFs
- Complicated
- Superior results
20Whats wrong with existing redundant Shrinkage?
- Mapping functions
- Naively borrowed from the unitary case.
- Independence assumption
- In the overcomplete case, the wavelet
coefficients are inherently dependent. - Minimization domain
- For the unitary case MFs are optimized in the
transform domain. This is incorrect in the
overcomplete case (Parseval is not valid
anymore). - Unsubstantiated
- Improvements are shown empirically.
21Questions we are going to address
- How to design optimal MFs for redundant bases.
- What is the role of redundancy.
- What is the role of the domain in which the MFs
are optimized. - We show that the shrinkage approach is comparable
to state-of-the-art approaches where MFs are
correctly designed.
22Optimal Mapping Function
- Traditional approach Descriptive
Modeling marginal p.d.f. of band k
MAP objective
x
23Optimal Mapping Function
- Suggested approach Discriminative
- Off line Design MFs with respect to a given set
of examples xei and yei - On line Apply the obtained MFs to new noisy
signals.
Denoising Algorithm
24Option 1 Transform domain independent bands
25Option 2 Spatial domain independent bands
26Option 3 Spatial domain joint bands
27The Role of Optimization Domain
- Theorem 1 For unitary transforms and for any set
of ?k -
- Theorem 2 For over-complete (tight-frame) and
for any set of ?k
28Unitary v.s. OvercompleteSpatial v.s. Transform
Domain
Over-complete
Unitary
Spatial domain
gt
gt
Transform domain
29Is it Justified to optimized in the transform
domain?
- In the transform domains we minimize an upper
envelope. - It is preferable to minimize in the spatial
domain.
30Optimal Design of Non-Linear MFs
- Problem How to optimize non-linear MFs ?
- Solution Span the non-linear ?k using a linear
sum of basis functions. - Finding ?k boils down to finding the span
coefficients (closed form).
Mapping functions
?k(y)
y
For more details see Hel-Or Shaked IEEE-IP,
Feb 2008
31- Let z?R be a real value in a bounded interval
a,b). - We divide a,b) into M segments qq0,q1,...,qM
- w.l.o.g. assume z?qj-1,qj)
- Define residue r(z)(z-qj-1)/(qj-qj-1)
a
b
z
z0,???,0,1-r(z),r(z),0,???q Sq(z)q
zr(z) qj(1-r(z)) qj-1
32The Slice Transform
- We define a vectorial extension
- We call this the
- Slice Transform (SLT) of z.
? ? ?
? ? ?
ith row
33The SLT Properties
- Substitution property Substituting the boundary
vector q with a different vector p forms a
piecewise linear mapping.
z
z
z
p
Sq(z)
q
z
z
z
q2
q3
q4
q1
34Back to the MFs Design
- We approximate the non-linear ?k with
- piece-wise linear functions
- Finding pk is a standard LS problem with a
closed form solution!
35Results
36Training Images
37Tested Images
38Simulation setup
- Transform used Undecimated DCT
- Noise Additive i.i.d. Gaussian
- Number of bins in SLT 15
- Number of bands 3x3 .. 10x10
39MFs for UDCT 8x8 (i,i) bands, i1..4, ?20
Option 1
40Why considering joint band dependencies produces
non-monotonic MFs ?
noisy image
Unitary MF
image space
Redundant MF
41Comparing psnr results for 8x8 undecimated DCT,
sigma20.
428x8 UDCT ?10
438x8 UDCT ?20
448x8 UDCT ?10
45Comparison with BLS-GSM
46Comparison with BLS-GSM
47Other Degradation Models
48JPEG Artifact Removal
49JPEG Artifact Removal
50Image Sharpening
51Image Sharpening
52Conclusions
- New and simple scheme for over-complete transform
based denoising. - MFs are optimized in a discriminative manner.
- Linear formulation of non-linear minimization.
- Eliminating the need for modeling complex
statistical prior in high-dim. space. - Seamlessly applied to other degradation problems
as long as scalar MFs are used for
reconstruction.
53Recent Results
- What is the best transform to be used (for a
given image or for a given set)?
54Thank You
The End