Title: Curvature%20Prior%20for%20MRF-based%20Segmentation%20and%20Shape%20Inpainting
1Curvature Prior for MRF-based Segmentation and
Shape Inpainting
This work was supported bu EU projects
FP7-ICT-247870 NIFTi and FP7-ICT-247525 HUMAVIPS
and the Czech project 1M0567 CAK
DAGM-OAGM 2012
Alexander Shekhovtsov, Pushmeet Kohli and Carsten
Rother
TexPoint fonts used in EMF. Read the TexPoint
manual before you delete this box. AAAAAAAA
2Motivation
- Would like to have a model tailored for the
specific shape class
Looked at higher-order MRFs and Field of Experts
Experts
Pixels
- Focus on the curvature cost as a simple example
of a shape model
3Motivation
- How can we model shapes with higher-order models?
- nonlinear function of linear filters -
continuous variables
Black and Roth. (2009) Field of Experts
hard pattern
Komodakis and Paragios (2009) Pattern-based
Higher Order Potentials
Rother et al. (2009) Sparse Higher Order
Potentials
expert state
soft pattern
4Curvature in Discrete Setting
- Most of the works go for explicit edge
representation (discrete setting)
Brukstain (2001) approximation
Cell-complex
Schoenemann et al. (2009) Schoenemann, Kahl ,et
al. (2011) Schoenemann, Kuang, et al.
(2011) Strandmark and Kahl (2011)
straight on a large scale, but highly penalized
- Convex relaxations in the continuous setting
Bredies et al. (2012), Goldluecke and Cremers
(2011)
5The Model
- Keep the segmentation pixel-wise but assess
curvature from a local window
window of the higher-order model
think of the curve with the lowest possible
curvature consistent with discretization
lager windows have a better chance of a more
accurate estimate
You would never thought of this curve, unless you
know something
6The Model
Rother et al. (2009)
densely, at every pixel location, there is a
higher-order term
restriction to the window
Energy
window locations
Higher-order term
for fixed y a modular (linear) functions of x
lower envelope of the modular functions of x
7The Model
in the minimum
or
8Minimization
- Good news minimization reduces to pairwise model
expands as
-join optimization in segmentation and latent
variables y
can combine with standard MRF models
- Bad news still hard to optimize ?
- BP-S/TRW-S (Kolmogorov, 2006) implementation
saving a factor of NP (number of patterns) memory
(lazy asymmetric message handling)
9BP Schedule dependence
Solution by BP-S (max-product) (swep from left
to right, from top to bottom)
Input (inpaint the gray area)
10Parallel (Synchronous) BP
Parallel BP
TRW-S
curvature (old model)
curvature length
curvature more length
11Learning
- For the case of curvature model, we have a
simpler learning problem we can learn the model
locally.
Generate smooth curves
Discretize
true curvature cost (analytic)
Fit the lower envelope model K-means like
algorithm, needs good initialization
12Learning
example (circle radius model cost)
cost function to learn
learned patterns
size 8x8 96 in total
predefined patterns assign 0 cost to
off-boundary locations
13Learning
discrete approximation vs. exact contour integral
Testing shape samples (analytic)
(overestimating)
14Shape Inpainting
area for inpainting
known segmentation
inpainted segmentation
15Shape Inpainting
16Shape Inpainting
17Segmentation
Input with user seeds
(saturation)
curvature strength
18Segmentation (skip)
Input with user seeds
Standard length regularization
regularization strength
19Segmentation (more)
- Extending the model we added artificially an ear
pattern. - its cost was tuned manually
after
before
20Curvature and Length Regularization
only curvature
curvature length
curvature more length
21Towards Object Inpainting
area for completion
our shape inpainting
interactive segmentation
Texture added automatically thanks to Barnes et
al. (2009)