Nonphotorealistic rendering - PowerPoint PPT Presentation

1 / 76
About This Presentation
Title:

Nonphotorealistic rendering

Description:

Images with photographic quality (eg Vermeer, 1632-1675, accused by critics of ... Are these images non-photorealistic renderings? ... – PowerPoint PPT presentation

Number of Views:33
Avg rating:3.0/5.0
Slides: 77
Provided by: DEN154
Category:

less

Transcript and Presenter's Notes

Title: Nonphotorealistic rendering


1
Nonphotorealistic rendering
  • Computational Photography, 6.882
  • Bill Freeman
  • Fredo Durand
  • May 9, 2006
  • Drawing from NPR Siggraph 1999 course, Green et
    al. npr_course_Sig99.pdf

2
Photorealism
  • Physically realistic computer graphics rendering
  • Images with photographic quality (eg Vermeer,
    1632-1675, accused by critics of being cold,
    inartistic, and displaying spiritual poverty).

http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
3
Are these images non-photorealistic renderings?
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
4
Non-photorealistic rendering
  • Expressive, artistic, painterly, interpretative
    rendering.
  • Not aspiring to realism.
  • Early work natural media emulation
  • Pen and ink
  • Watercolor
  • Oil on canvas
  • Attempts to capture the low-level style.
  • Simulations of technical illustration.

http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
5
NPAR 2002
6
Comparing photorealism and NPR (Stuart Green)
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
7
(No Transcript)
8
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
9
Statistical techniques to simulate expression
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
10
Paintings are not solutions to well-posed
problems
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
11
Daniel Teece
http//pages.cpsc.ucalgary.ca/mario/npr/projects/
sigg03/lec8/hand_1.pdf
12
Organization of NPR methods
  • Automated methods
  • 2-d processing
  • 3-d processing
  • Interactive methods
  • 2-d processing
  • 3-d processing

13
Organization of NPR methods
  • Automated methods
  • 2-d processing
  • 3-d processing
  • Interactive methods
  • 2-d processing
  • 3-d processing

14
2/2.5 D, no user intervention
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
15
http//www.mrl.nyu.edu/publications/hertzmann-thes
is/hertzmann-thesis-72dpi.pdf
16
Issues in image style translation
  • Fitting
  • Translation

17
http//people.csail.mit.edu/billf/papers/p33-t_fre
eman.pdf
18
http//people.csail.mit.edu/billf/papers/p33-t_fre
eman.pdf
19
Input traced line drawing
This example will illustrate the tension between
fitting and translation
http//people.csail.mit.edu/billf/papers/p33-t_fre
eman.pdf
20
Input drawing
1-NN fit to input, style 1
Translation to style 2
http//people.csail.mit.edu/billf/papers/p33-t_fre
eman.pdf
21
Input drawing
1-NN fit to input, style 1
Translation to style 2
Bad fit, good translation
http//people.csail.mit.edu/billf/papers/p33-t_fre
eman.pdf
22
Input drawing
5904-NN fit to input, style 1
Translation to style 2.
http//people.csail.mit.edu/billf/papers/p33-t_fre
eman.pdf
23
Input drawing
5904-NN fit to input, style 1
Translation to style 2.
Good fit, bad translation
http//people.csail.mit.edu/billf/papers/p33-t_fre
eman.pdf
24
Input drawing
6-NN fit to input, style 1
http//people.csail.mit.edu/billf/papers/p33-t_fre
eman.pdf
25
Input drawing
6-NN fit to input, style 1
Translation to style 2
Good fit, good translation
http//people.csail.mit.edu/billf/papers/p33-t_fre
eman.pdf
26
style 1
style 2
style 3
http//people.csail.mit.edu/billf/papers/p33-t_fre
eman.pdf
27
http//people.csail.mit.edu/billf/papers/p33-t_fre
eman.pdf
28
6-NN fit to input, style 1
Translation to style 3
http//people.csail.mit.edu/billf/papers/p33-t_fre
eman.pdf
29
http//mrl.nyu.edu/projects/image-analogies/
30
http//mrl.nyu.edu/publications/image-analogies/an
alogies-72dpi.pdf
31
Image analogies applications
32
For painterly style translation, how get the A,
A image pairs?
33
http//mrl.nyu.edu/projects/image-analogies/
34
http//mrl.nyu.edu/projects/image-analogies/
35
http//mrl.nyu.edu/projects/image-analogies/
36
Texture Transfer
  • Take the texture from one object and paint it
    onto another object
  • This requires separating texture and shape
  • Thats HARD, but we can cheat
  • Assume we can capture shape by boundary and rough
    shading

Then, just add another constraint when sampling
similarity to underlying image at that spot
http//people.csail.mit.edu/billf/papers/efrosFree
man.pdf
37
Source texture
Target image
http//people.csail.mit.edu/billf/papers/efrosFree
man.pdf
38
http//people.csail.mit.edu/billf/papers/efrosFree
man.pdf
39
A
A
40
(No Transcript)
41
B
42
B
43
B
44
I think this one fails
45
Organization of NPR methods
  • Automated methods
  • 2-d processing
  • 3-d processing
  • Interactive methods
  • 2-d processing
  • 3-d processing

46
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
47
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
48
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
49
Gooch and Gooch
  • Concentrate on the material property and shading
    aspects of technical illustration.

50
Some characteristics of technical illustrations
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
51
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
52
Technical illustrations
  • Lines

53
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
54
Some parameterization dependent lines
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
55
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
56
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
57
Line weight variations
Line weight varied to emphasize perspective
Outer edges thicker
Equal weight
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
58
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
59
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
60
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
61
Technical illustrations
  • Shading

62
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
63
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
64
(No Transcript)
65
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
66
Encoding surface orientation by color temperature
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
67
Direction dependent illumination color
68
Combining color-temp surface orientation coding
with some tonal variations in object color
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
69
Parameter setting 1
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
70
Parameter setting 2
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
71
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
72
Metal object with anisotropic reflections
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
73
Metal object with anisotropic reflections
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
Lines are streaked in the direction of the axis
of minimum curvature, parallel to the milling
axis.
74
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
75
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
76
3D, little user intervention
http//www.cs.utah.edu/npr/papers/npr_course_Sig99
.pdf
Write a Comment
User Comments (0)
About PowerShow.com