Lecture 8_ Point Processing and More Filtering by malj

VIEWS: 0 PAGES: 14

• pg 1
```									CS 585 Computational Photography

Nathan Jacobs
Today’s Agenda
• Group discussion
– Assignment 1
– Seam carving assignment

• Recap from last time

some terminology
• compositing: combining two (or more) images
– often using an alpha channel
– how do you transition between images?
• segmentation: dividing image up into regions
of “similar” pixels
• matting: soft segmentation to pull an object
from the background
Laplacian Pyramids
lowpass Images (gaussian)

bandpass Images (laplacian)
laplacian
level
4

laplacian
level
2

laplacian
level
0

left pyramid   right pyramid   blended pyramid
Laplacian Pyramid Blending
• We decomposed our image into a set of
Difference-of-Gaussian images and a low-res
image

• Now lets look at 1st order derivatives
• Let us now look at 1st order derivatives
– No need for low-res image
• captures everything (up to a constant)
– Idea:
• Differentiate
• Blend
• Reintegrate
James McCann and Nancy S. Pollard. Real-time Gradient-domain Painting,
ACM Transactions on Graphics (SIGGRAPH 2008),
1.    mask = double(im1 > 15);
2.
3.    im1 = 1:30; im2 = 5*sin(linspace(0,15,30));
4.
7.
10.   imBlendGradient(1) = imBlend(1); % fix one value (should really fix both ends)
12.
13.   figure(1);
14.   subplot(2,2,1), plot(im1), title('signal one')
15.   subplot(2,2,2), plot(im2), title('signal two')
16.   subplot(2,2,3), plot(imBlend), title('direct blending')

• Trickier in 2D:
– Take partial derivatives dx and dy (the gradient field)
– Fiddle around with them (smooth, blend, feather, etc)
– Reintegrate
• But now integral(dx) might not equal integral(dy)
– Find the most agreeable solution
• Equivalent to solving Poisson equation
• Can use FFT, deconvolution, multigrid solvers, etc.
– Show linear constraints on board…
Perez et al., 2003
Perez et al, 2003

editing

• Limitations:
– Can’t do contrast reversal (gray on black -> gray
on white)
– Colored backgrounds “bleed through”
– Images need to be very well aligned
next time
• Graph Cut Based Methods