Blending and Pyramids Blending Weve aligned our images What now Averaging Weighted averaging minmaxmedian Noise reduction by Averaging 2 Shots 4 Shots 8 Shots 16 Shots Noise Reduction by Averaging ID: 225766
Download Presentation The PPT/PDF document "CS448f: Image Processing For Photography..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
CS448f: Image Processing For Photography and Vision
Blending and PyramidsSlide2
Blending
We’ve aligned our images. What now?
Averaging
Weighted averaging
min/max/medianSlide3
Noise reduction by AveragingSlide4
2 ShotsSlide5
4 ShotsSlide6
8 ShotsSlide7
16 ShotsSlide8
Noise Reduction by Averaging
We’re averaging random variables X and Y
Both have variance S
2
Variance of X+Y = 2S
2
Std.Dev. of X+Y = sqrt(2) . S
Std.Dev of (X+Y)/2 = sqrt(2)/2 . S
Ie, every time we take twice as many photos, we reduce noise by sqrt(2)Slide9
Noise Reduction by Averaging
Average 4 photos: noise gets reduced 2x
Average 8 photos: noise gets reduced 3x
Average 16 photos: noise gets reduced 4xSlide10
Noise Reduction by Median
(demo)Slide11
Median v
AverageSlide12
Median
v AverageSlide13
Can we identify the bad pixels?
They’re unlike their neighbours
Instead of averaging, weighted average
where weight = similarity to neighbours
Slide14
Weighted AverageSlide15
Can we identify the bad pixels?
They’re unlike their neighbours
Instead of averaging, weighted average
where weight = similarity to neighbours
Favors blurriness
Slide16
InputSlide17
Other uses of Median
Removing Transient Occluders
(live demo)
(Gates demo)
(surf demo)Slide18
Panorama StitchingSlide19
Panorama StitchingSlide20
Panorama StitchingSlide21
Panorama StitchingSlide22
Panorama StitchingSlide23
Multiple Exposure FusionSlide24
Multiple Exposure FusionSlide25
Multiple Exposure FusionSlide26
Multiple Exposure FusionSlide27
Multiple Exposure FusionSlide28
Multiple Exposure FusionSlide29
Multiple Exposure FusionSlide30
Multiple Exposure FusionSlide31
Multiple Exposure FusionSlide32
Multiple Exposure FusionSlide33
Multiple Exposure FusionSlide34
Focus FusionSlide35
Focus FusionSlide36
Focus FusionSlide37
Focus FusionSlide38
Focus FusionSlide39
Pyramids
We’ve been breaking images into two terms for a variety of apps
Coarse + Fine
More generally we can break it into many terms:
Very coarse + finer + finer ... + finest.Slide40
Pyramids
We can do this by blurring more and more:Slide41
Pyramids
And then
(optionally) taking
differences
-
-Slide42
Pyramids
The coarse layers can be stored at low res.
Gaussian
Pyramid
Laplacian
PyramidSlide43
Pyramids
How much memory does this use?Slide44
Pyramid Uses:
Sampling arbitrarily sized Gaussians
Equalizing an image
The different levels represent different frequency ranges
We can scale each frequency level and recombine
Blending multiple imagesSlide45
Pyramid Blending
Key Insight:
Coarse
structure
should blend very slowly between images (lots of feathering), while fine details should transition more quickly
.
More robust to tricky cases than plain old compositingSlide46
Inputs:Slide47
Compositing: Hard MaskSlide48
Compositing: Soft MaskSlide49
Multi-Band BlendingSlide50
Exposure Fusion
http://research.edm.uhasselt.be/~tmertens/papers/exposure_fusion_reduced.pdf