Академический Документы
Профессиональный Документы
Культура Документы
Downsampling
Matthew Trentacoste
Rafał Mantiuk
Wolfgang Heidrich
2
Is the photograph blurry?
3
Is the photograph blurry?
3
Is the photograph blurry?
3
Motivation
4
Motivation
2 Mp
• Sensors higher resolution than displays
4
Motivation
2 Mp
• Sensors higher resolution than displays
4
Motivation
5
Organization
• Related work
• Blur estimation
• Evaluation + conclusion
6
Related work
• Blur perception
[Cufflin 2007][Chen 2009]
[Mather 2002][Held 2010]
• Intelligent upsampling
[Fattal 2007][Kopf 2007][Shan 2008]
• Seam carving
[Avidan 2007]
[Rubenstein 2009,2010]
7
Related work
• Blind deconvolution
[Lam 2000][Fergus 2006]
• Blur magnification
[Bae 2007][Samadani 2007]
8
Perceptual study
• Blur-matching experiment
9
Perceptual study
• Blur-matching experiment
9
Perceptual study
10
Matching results
• Matching blur larger than reference
blur, smaller images appear sharper
11
Matching results
• Matching blur larger than reference
blur, smaller images appear sharper
11
Blur appearance model
'RZQVDPSOHGLPDJHEOXU
!
ςm = ς 2d + S 2 20
•
5
Full model provides accurate and
plausible fit of the measured data in the 0
0 5 10 15 20 25 30 35 40
spatial domain
)XOOVL]HLPDJHEOXUFXWïRIIIUHTXHQF\nr>F\FOHVSHUGHJUHH@
12
Blur appearance model
'RZQVDPSOHGLPDJHEOXU
!
ςm = ς 2d + S 2 20
•
5
Full model provides accurate and
plausible fit of the measured data in the 0
0 5 10 15 20 25 30 35 40
spatial domain
)XOOVL]HLPDJHEOXUFXWïRIIIUHTXHQF\nr>F\FOHVSHUGHJUHH@
1
S(ς r , d) = −0.893 log (d)+0.197 1
2 2 ( ς r − 1.64) + 1.89
12
Blur appearance model
'RZQVDPSOHGLPDJHEOXU
!
ςm = ς 2d + S 2 20
0.3
0.2
x2 data
Downsampled
x4 data
x4 model
0.1
•
5
Full model provides accurate and x8 data
x8 model
plausible fit of the measured data in the 0
0 50.05 10 0.115 0.15
20 250.2 30 0.2535 40
Full size image blur radius n [vis deg]
spatial domain
)XOOVL]HLPDJHEOXUFXWïRIIIUHTXHQF\n
r r
>F\FOHVSHUGHJUHH@
1
S(ς r , d) = −0.893 log (d)+0.197 1
2 2 ( ς r − 1.64) + 1.89
12
Blur estimation
• Spatially-variant estimate of the
blur present at each pixel of image
• Downsampling approximates a
blur-free image
13
Blur estimation
Edge Derivative
14
Blur estimation
Edge Derivative
2x
14
Blur estimation
Edge Derivative
2x
4x
14
Blur estimation
Edge Derivative
2x
4x
8x
14
Blur estimation
2
1 − √x
width: σ g (x, σ) = √
2πσ 2
e 2σ 2
15
Blur estimation
2
1 − √x
width: σ g (x, σ) = √
2πσ 2
e 2σ 2
15
Blur estimation
Downsampled
Edge Gradient magnitude scale space
2
1 − √x
width: σ g (x, σ) = √
2πσ 2
e 2σ 2
15
Blur estimation
Downsampled
Edge Gradient magnitude scale space
2
1 − √x
width: σ g (x, σ) = √
2πσ 2
e 2σ 2
15
Blur estimation
Downsampled
Edge Gradient magnitude scale space
2
1 − √x
width: σ g (x, σ) = √
2πσ 2
e 2σ 2
15
Blur estimation
original gradients thumbnail gradients
1 1
! ≈ ! "# 2 $ %
2πσo2 σo 2
2π d + (βj)
d downsample
j scale space level
β quantization term
16
Blur estimation
original gradients thumbnail gradients
1 1
! ≈ ! "# 2 $ %
2πj 2 j 2
2π d + (βj)
d downsample
j scale space level
β quantization term
16
Blur estimation
original gradients thumbnail gradients
1 1
γ !2πj 2
= ! "# 2 $
j 2
%
2π d + (βj)
d downsample
j scale space level
β quantization term
16
Blur estimation
original gradients thumbnail gradients
1 1
γ !2πj 2
= ! "# 2 $
j 2
%
2π d + (βj)
1
d downsample γ = !" #
j scale space level 1 2
d + β2
β quantization term
16
Blur estimation
original gradients thumbnail gradients
1 1
γ !2πj 2
= ! "# 2 $
j 2
%
2π d + (βj)
1
d downsample γ = !" #
j scale space level 1 2
d + β2
β quantization term
16
Blur estimation
17
Blur synthesis
18
Blur synthesis
18
Blur synthesis
18
Blur synthesis
18
Blur synthesis
18
Blur synthesis
18
Blur synthesis
• To produce final image blur each level scalespace lσj
by corresponding σa , linearly blend for non-integer σa
Scalespace
+ =
19
Evaluation Naive
Samadani
gamma=4
Samadani
gamma=.5
Blur-Aware
20
Evaluation
Naive
Blur-Aware
Naive
Blur-Aware
21
Evaluation
Original 2x naive 2x blur-aware 4x naive 4x aware
%&/0/$() !"#$%&'() !"#*)+&,(-(&. 1"#$%&'() 1"#*)+&,(-(&.
1"#$%&'() 1"#*)+&,(-(&.
1"#*)+&,(-(&. !"#$%&'() !"#*)+&,(-(&.
4x naive 4x aware 2x naive 2x blur-aware Original
22
Conclusion
• Fully automatic image resizing operator that uses a
perceptual metric to preserve image appearance
• Future work:
Other models like camera optics to enhance blur
Extending principle to other attributes such as noise or
contrast
23
Thanks!
( you and our sponsors ) Research Chair