art and perception - mit csailpeople.csail.mit.edu/fredo/artandperception2.pdf · 2001. 6. 30. ·...
TRANSCRIPT
1
The Art and Science of Depiction 1
The Art and Science of Depiction
Frédo DurandMIT
Lab for Computer Science
2
The Art and Science of Depiction 3
From CG and geometry…
Arc of the skeleton
Q
Visual event ev
Array indexed by the polygons Search tree
veQ
P
P
The Art and Science of Depiction 4
… to make-up and swimming-suits
3
The Art and Science of Depiction 5
Overview of the talk• No computer-graphics research• Preliminary and not-so-preliminary reflections
about images• 1st part:
– Context and goals(Raising expectations)
• 2nd part: – Overview of the class
The Art and science of depiction– (Failing the expectations)
The Art and Science of Depiction 6
Motivations: Post-PhD blues…• Why do our image lack aesthetic?• What’s our goal?• Where Do We Come From? What Are We?
Where Are We Going?
4
The Art and Science of Depiction 7
Motivations• What is “Realism”? What is “Photorealism”?• Are photographs realistic?• Are photographs photorealistic?• What is Non-Photorealistic Rendering?
The Art and Science of Depiction 8
Non-Photorealistic Rendering• A variety of awesome techniques and solutions• But what are the issues?• Difficulty of classification• Each paper deals with several problems• Lack of inter-operability
5
The Art and Science of Depiction 9
Why make images?• Educational• Tell story• Simulation• Design• Sign• Guide task• Visualization• Search• Analysis
• Create shape• Expression• Beauty• Shock• Medical• Humor• Faith• Prevention• Etc.
• Not one single class of images• Thus, there may be many ways to make images• CG focuses too much on one of them
The Art and Science of Depiction 10
Non-realism vs. realism• Non-realism is MORE than degraded realism
– E.g. clarity, selection, abstraction, etc.
6
The Art and Science of Depiction 11
Realism vs. realism• A realistic image can be MORE than realistic• E.g. dodging and burning
– During the print– Locally darken or lighten using a mask
The Art and Science of Depiction 12
Dodging and Burning• Ansel Adams• Clearing Winter Storm
7
The Art and Science of Depiction 13
Generic pictorial issues• A lot of issues are universal• E.g. oil painting / photograph
Titian
The Art and Science of Depiction 14
Generic pictorial issues• Contrast is reinforced at the occlusion silhouette• Tone modification / haze
Titian
8
The Art and Science of Depiction 15
Computer Graphics Imagery• Rendering is efficient• Hardware is fast• 3D content creation becomes the bottleneck• Most CG images are still not very compelling
The Art and Science of Depiction 16
The one-way pipeline• Rendering pipeline, rendering equation• From 3D model to image• No feedback
3D geometry
Material attributes
Light sources
Image
Viewpoint
Light simulation
Projection
Rasterization, etc.
9
The Art and Science of Depiction 17
Feedback and Darwinian selection• Picture production is a trial and error process• The artist tries pictorial techniques, constantly
judges the current state of the picture and reacts accordingly
The Bull by Picasso
The Art and Science of Depiction 18
What can we do?• Simulate the feedback
– Optimization approaches– Perception/artistic-based “metric”– What are the goals?
• Bypass the feedback– What are the pictorial issues?– What are the pictorial techniques?– Hopefully inverse the feedback
• Try to understand what is going on and what we’re trying to do!
10
The Art and Science of Depiction 19
What and whom for?• Trained image makers
– Understand what they need– Provide more relevant tool
• Image-dummies– Automatic and semi-automatic– E.g. “gorgeous image” for CAD– E.g. “digital photo beautifier”
• Computers (100% automatic)– E.g. can we transfer the art and
craft of cinema into games?
The Art and Science of Depiction 20
Can artists tell us?• Well, a lot of translation is necessary• Their feedback loop is extremely good• But it is often an inaccessible black box
11
The Art and Science of Depiction 21
Can art historians tell us?• Well, a lot of translation is necessary• They know what is good in an image• Their language is descriptive, not generative• Often limited to 14th-19th century Western art• But recent art history works with general images
The Art and Science of Depiction 22
Can perception scientists tell us?• Well, a lot of translation is necessary• Experimental results
– E.g. colors, perspective perception
• Provide framework to pictorial techniques– Corresponding human visual mechanisms– Unfortunately, often no quantitative prediction– Suggests relevant “dimensions” or issues
• Unfortunately complex images are…too complex
12
The Art and Science of Depiction 23
Can perception & art history tell us?• Well, some translation is necessary• But very fruitful• That is the topic of this talk!
The Art and Science of Depiction 24
Can we tell them something?• Well, a lot of translation is necessary• Raise interesting questions• Generative approach to pictures• Systematic validation
– We cannot omit anything (you get what you ask for)– Parallel: computer-vision showed the complexity of
human vision
13
The Art and Science of Depiction 25
Towards picture sciences ?
• Perception
• Art History
• Visual Arts
• Computational Vision
• Computer Graphics
• A paradigm: Language sciences
The Art and Science of Depiction 26
The Art and Science of Depiction• Graduate class at MIT (but undergrads as well)• Multidisciplinary• Students from Architecture, Computer Science,
Cognitive Sciences, Media Art & Science
14
The Art and Science of Depiction 27
Other goals• Multidisciplinary, make connections• Different viewpoint on picture• Correct scientific errors in art books
• Excuse to talk about cool stuff
• Excuse to look at cool pictures
The Art and Science of Depiction 28
Disclaimer & epistemology• What will be described are
connections, correlations, NOT truths, causalities, explanations
• Moreover, they are often hypothesis not yet verified
• But we hope they offer insights
15
The Art and Science of Depiction 29
Plan• Visual system and art
• Limitations of medium: compensation and accentuation
• Representation system
The Art and Science of Depiction 30
Beware of the El-Greco Fallacy• El-Greco, elongated characters• Were supposed due to astigmatism• However, pictures and real people
would have been stretched equally• Almost as fallacious as assuming
painting should be inverted becauseour eyes invert what we see
16
The Art and Science of Depiction 31
Vision as information processing• Input: retinal image• Output: 3D layout, object recognition, etc.
Retinalimage
IntermediateData
Sceneunderstanding
Processing Processing
The Art and Science of Depiction 32
Computational theory of vision• Marr’s stages (extended by Palmer et al.)• Human and Computer Vision• Classification of different kinds of processes• Has proved fruitful in art studies
View-centered Object-centeredExtrinsic Intrinsic
17
The Art and Science of Depiction 33
Retinal image• Intensity
Cup
The Art and Science of Depiction 34
Image-based (primary sketch)• Contrast, edge detection
Cup
18
The Art and Science of Depiction 35
Surface-based• Visible surfaces, organization• Distance, orientation
Cup
Local orientation
The Art and Science of Depiction 36
Object-based• 3D properties, structure• Nature of the description highly discussed
Cup
19
The Art and Science of Depiction 37
Category-based• Recognition, category, function
Cup
The Art and Science of Depiction 38
Feedback• Bottom-up and top-bottom
Cup
20
The Art and Science of Depiction 39
Evolution of children’s drawings• First draw what they
know (object-based)• Then what they see
(towards retinal)• Asked to draw a table
Child’s view
7.4 9.7
11.9 13.6
14.3 13.7
Class of drawing & average age
The Art and Science of Depiction 40
3D and 2D attributes• Show a dice to children (~6-7) • They usually draw a rectangle• The rectangle could stand for one face
21
The Art and Science of Depiction 41
3D and 2D attributes• Show coloured or numbered dice to children (6-7) • The still draw a rectangle• But different colours or many points
The Art and Science of Depiction 42
3D and 2D attributes• Show coloured or numbered dice to children (6-7) • The still draw a rectangle• But different colours or many points• The rectangle stands for the whole dice• The notion of 3D object with corners is translated
as a 2D object with corners
22
The Art and Science of Depiction 43
Relation to pictures• Different classes of pictures for different stages• Not a strict classification, not a cultural judgment
View-centered Object-centeredExtrinsic Intrinsic
The Art and Science of Depiction 44
Relation to pictures• Chinese painting refuse extrinsic, only essential• No shadow
View-centered Object-centeredExtrinsic Intrinsic
23
The Art and Science of Depiction 45
Retinal image• Impressionism• Photography
The Art and Science of Depiction 46
Retinal image• Impressionism• Not so simply classified
24
The Art and Science of Depiction 47
Image-based• Line Drawing
The Art and Science of Depiction 48
Intermediate• View-based• Cues for surface-based
feature extractionare enhanced– Depth cues– Orientation cues
• No subjective feature(e.g. lighting)
25
The Art and Science of Depiction 49
Higher level• Primitive art• Cubism• Schema• “What I know”
The Art and Science of Depiction 50
Higher level• Primitive art• Cubism• Schema• “What I know”
26
The Art and Science of Depiction 51
Expressionism• “What I feel”
Othermode
The Art and Science of Depiction 52
Gaze movement• We need to align the fovea with relevant features
27
The Art and Science of Depiction 53
Gaze movement• We need to align the fovea with relevant features• Saccadic exploration
– Path– Fixation time
The Art and Science of Depiction 54
Gaze attraction & focal zone• E.g. Through contrast
28
The Art and Science of Depiction 55
One focal zone • Arthus-Bertrand• Striking but…
The Art and Science of Depiction 56
Two focal zones• Robert Mapplethorpe
Self-portrait, 1988• More dynamic
29
The Art and Science of Depiction 57
Triple focus and subject gaze• Robert Doisneau
Les Gosses de la place Hebert
• More lively
The Art and Science of Depiction 58
Turner’s Loire journey• The gaze follows the journey
30
The Art and Science of Depiction 59
Focal point conflict• Bottom-up is different
from top down• Makes image dynamic
The Art and Science of Depiction 60
Fixation time & style• Depends on style “complexity”• Shorter fixation for more complex style
31
The Art and Science of Depiction 61
Advertisement and focal points• Evolution of saliency
The Art and Science of Depiction 62
Plan• Visual system and art
• Limitations of medium: compensation and accentuation
• Representation system
32
The Art and Science of Depiction 63
Limitations of the medium• Flatness• Finite size, frame• Unique viewpoint• Static• Contrast and gamut
• Can be eliminated• Can be compensated• Can be accentuated
The Art and Science of Depiction 64
Eliminating flatness• Stereo display
33
The Art and Science of Depiction 65
Enhancing depth through contrast
The Art and Science of Depiction 66
Accentuating flatness• Monet• Occlusion
boundariesare barely visible
• Retinalstage ratherthan surface
34
The Art and Science of Depiction 67
Accentuating – dissonance• Magritte• Occlusions
are reversed
The Art and Science of Depiction 68
The contrast is limited• Real world: 10-6 to 106
• Picture: 1 to 50, 1 to 300 at best
10-6 106
10-6 106
High dynamic range
Low contrast
35
The Art and Science of Depiction 69
Low contrast is also an advantage• W. Eugene Smith photo of Albert Schweitzer• 5 days to print!• Things can be related because the intensity is
more similar• Balance,
composition
The Art and Science of Depiction 70
The image is static – Motion Blur
36
The Art and Science of Depiction 71
Multiple Snapshots• Marcel Duchamp
Nude Descending a Staircase1912
The Art and Science of Depiction 72
Static image & composition• Tak Kwong Chan
The Horse –Away He Goes 1980
• Both static and dynamicqualities :the limitation is a richness
37
The Art and Science of Depiction 73
Plan• Visual system and art
• Limitations of medium: compensation and accentuation
• Representation system
The Art and Science of Depiction 74
Plan• Visual system and visual arts
• Limitations of medium: compensation and accentuation
• Representation system
38
The Art and Science of Depiction 75
Representation systems: goals• Coarse-grain description of style• Independent systems, independent decisions• Description and comparison• Potentially generative (for NPR)
The Art and Science of Depiction 76
A paradigm: Cartography• A map is a depiction of a reality• Can be more efficient than photo• There is no perfect universal solution• The systems are usually explicit!
39
The Art and Science of Depiction 77
Map making• Which information
will be represented
• Projection• Which kind of
symbols will be used• Colour codes
The Art and Science of Depiction 78
Projection
40
The Art and Science of Depiction 79
Projection: Topological• Beck’s map of London underground, 1931
The Art and Science of Depiction 80
Projection: Topographical• London underground
41
The Art and Science of Depiction 81
“Metaphoric” Projection
The Art and Science of Depiction 82
Error:Columbus's map
42
The Art and Science of Depiction 83
Error/choice/distortion• Descelier, 1546
The Art and Science of Depiction 84
Error/choice/distortion• Descelier,
1546• E.g. huge
elephant
43
The Art and Science of Depiction 85
Denotation (Primitive & Dimensions)
The Art and Science of Depiction 86
Denotation (Primitive & Dimensions)
44
The Art and Science of Depiction 87
Colour system• E.g. elevation
The Art and Science of Depiction 88
Representation system• Drawing
• Denotation
• Tone & color
45
The Art and Science of Depiction 89
Final conclusions and future work• What the hell can we do with all this?
The Art and Science of Depiction 90
To Be Continued…
46
The Art and Science of Depiction 91
Representation systems• Drawing and projection• Denotation• Tone & colour
• The two first systems are classical• Because painting was the only recognized art
form
The Art and Science of Depiction 92
Drawing system• Linear perspective
• Orthographic
• Topological
• Other
47
The Art and Science of Depiction 93
Denotation system• Silhouette: 2D (regions)• Line Drawing: 1D (lines)• Optical: 0D (points)
The Art and Science of Depiction 94
Tone & colour system• Extrinsic (outgoing light)• Intrinsic (reflectance properties)• Other, e.g. symbolic
48
The Art and Science of Depiction 95
Marks vs. primitive• Mosaic• Primitives = lines• Marks = points
(or small regions)
The Art and Science of Depiction 96
Marks vs. primitive• Paul Siemsen
Picasso
49
The Art and Science of Depiction 97
Style• Coarse-grain style
– Different categories of drawing, denotation, tone
• Finer-grain• Local style
• Parameterization • Capture
– Automatically deduce style from 3D renderings– (semi)-Automatically capture style from image(s)
The Art and Science of Depiction 98
Shading and highlighting
50
The Art and Science of Depiction 99
Corrective Make Up• Depending on
the shape of the face
The Art and Science of Depiction 100
Corrective lighting
51
The Art and Science of Depiction 101
An example
The Art and Science of Depiction 102
Is it fair?
52
The Art and Science of Depiction 103
Touch-up: too dark face
The Art and Science of Depiction 104
Touch-up: silhouette
53
The Art and Science of Depiction 105
Touch-up: undesirable lines
The Art and Science of Depiction 106
Touch-up: stretch and arm
54
The Art and Science of Depiction 107
Deforming lens• Deform one part of the
frame• Stretched arm and legs
The Art and Science of Depiction 108
Perspective distortion• The sphere is projected
as an ellipse
55
The Art and Science of Depiction 109
Perspective distortion• The sphere is projected
as an ellipse
The Art and Science of Depiction 110
Leonardo & contradictions• Wide angle vision
56
The Art and Science of Depiction 111
Leonardo & contradictions• Wide angle vision • Lateral recession
The Art and Science of Depiction 112
Perspective distortion• Portrait: distortion with wide angle
Wide angle Standard Telephoto