Architectural Procedural Models Jan Bene , Tom Kelly, Filip Dchtrenko - - PowerPoint PPT Presentation

architectural procedural models
SMART_READER_LITE
LIVE PREVIEW

Architectural Procedural Models Jan Bene , Tom Kelly, Filip Dchtrenko - - PowerPoint PPT Presentation

On Realism of Architectural Procedural Models Jan Bene , Tom Kelly, Filip Dchtrenko , Jaroslav Kivnek, Pascal Mller Quick Quiz 2 Jan Bene - On Realism of Architectural Procedural Models Quick Quiz Computer Generated Photograph


slide-1
SLIDE 1

On Realism of Architectural Procedural Models

Jan Beneš, Tom Kelly, Filip Děchtěrenko, Jaroslav Křivánek, Pascal Müller

slide-2
SLIDE 2

Quick Quiz

2

Jan Beneš - On Realism of Architectural Procedural Models

slide-3
SLIDE 3

Quick Quiz

3

Jan Beneš - On Realism of Architectural Procedural Models

Computer Generated Photograph

slide-4
SLIDE 4

Overview

4

Jan Beneš - On Realism of Architectural Procedural Models

Procedural Modeling & Realism Questions Previous Work Experiment & Data Acquisition Answers

slide-5
SLIDE 5

Procedural Modeling

  • Procedural

modeling

– Tool for artists – Or fully automatic – Wide range of

  • utputs
  • Wide use

5

Jan Beneš - On Realism of Architectural Procedural Models

[Independence Day] [Palubicki09]

slide-6
SLIDE 6

Procedural Modeling

  • Procedural

modeling

– Tool for artists – Or fully automatic – Wide range of

  • utputs
  • Wide use

6

Jan Beneš - On Realism of Architectural Procedural Models

[Independence Day] [Palubicki09]

slide-7
SLIDE 7

Realism

Realism  Plausibility  Immersion

  • Model & material & display
  • Should be studied
  • For procedural modelling

7

Jan Beneš - On Realism of Architectural Procedural Models

[Velocipedia, Gianluca Gimini]

slide-8
SLIDE 8

Realism

Realism  Plausibility  Immersion

  • Model & material & display
  • Should be studied
  • For procedural modelling

8

Jan Beneš - On Realism of Architectural Procedural Models

[Velocipedia, Gianluca Gimini]

slide-9
SLIDE 9

What we did

9

Jan Beneš - On Realism of Architectural Procedural Models

Procedural architecture

slide-10
SLIDE 10

What we did

10

Jan Beneš - On Realism of Architectural Procedural Models

User Study

slide-11
SLIDE 11

Question #1

(1) Can people tell procedurally generated buildings from real ones?

11

Jan Beneš - On Realism of Architectural Procedural Models

slide-12
SLIDE 12

Question #2

(2) Is realism carried in the detail or in the larger structure?

12

Jan Beneš - On Realism of Architectural Procedural Models

slide-13
SLIDE 13

Question #2

(2) Is realism carried in the detail or in the larger structure?

13

Jan Beneš - On Realism of Architectural Procedural Models

slide-14
SLIDE 14

Question #2

(2) Is realism carried in the detail or in the larger structure?

14

Jan Beneš - On Realism of Architectural Procedural Models

slide-15
SLIDE 15

Question #3

(3) What factors do the users think influence the perception of realism?

15

Jan Beneš - On Realism of Architectural Procedural Models

I think…

slide-16
SLIDE 16

Questions

(1) Can people tell procedurally generated buildings from real ones? (2) Is realism carried in the detail or in the larger structure? (3) What factors do the users think influence the perception of realism?

16

Jan Beneš - On Realism of Architectural Procedural Models

I think…

slide-17
SLIDE 17

Previous Work

17

slide-18
SLIDE 18

Previous Work - Realism

18

Jan Beneš - On Realism of Architectural Procedural Models

“There is no dirt, no dust, no fingerprints on the glass table…simply too beautiful, too clean and polished…” [Reinhard13]

slide-19
SLIDE 19

Previous Work - Realism

19

Jan Beneš - On Realism of Architectural Procedural Models

CG2Real [Johnson11]

slide-20
SLIDE 20

Previous Work - Realism

20

Jan Beneš - On Realism of Architectural Procedural Models

[Rademacher01]

slide-21
SLIDE 21

Previous Work - Buildings

21

Jan Beneš - On Realism of Architectural Procedural Models

  • Building generation

– Grammar [Stiny80, Wonka03, Muller06, Schwarz15] – Data [Fan16] – Sketch [Nishida16] – Predefined parts [Kalogerakis12, Talton12]

slide-22
SLIDE 22

Previous Work - Miscellaneous

22

Jan Beneš - On Realism of Architectural Procedural Models

  • Machine Learning

– What makes Paris look like Paris [Doersch12] – Architectural Style Recognition [Mathias11]

  • Image Quality & Similarity

– Visible Differences Predictor [Daly92] – Visual Equivalence and Aggregates [Ramanarayanan07,08] – Structural Similarity - SSIM [Wang04]

slide-23
SLIDE 23

Experimental Setup

23

slide-24
SLIDE 24

Datasets

24

Jan Beneš - On Realism of Architectural Procedural Models

Favela Medieval Paris Venice

slide-25
SLIDE 25

Datasets

25

Jan Beneš - On Realism of Architectural Procedural Models

Favela Medieval Paris Venice Photos Computer Generated

slide-26
SLIDE 26

X

Classification Screen

26

Jan Beneš - On Realism of Architectural Procedural Models

X

slide-27
SLIDE 27

Blurs

27

Jan Beneš - On Realism of Architectural Procedural Models

13px blur 7px blur 1px – no blur 55px blur 32px blur 25px blur

slide-28
SLIDE 28

Summary

28

Jan Beneš - On Realism of Architectural Procedural Models

TRAINING

slide-29
SLIDE 29

Summary

29

Jan Beneš - On Realism of Architectural Procedural Models

Venice-55px Medieval-55px Paris-55px Favela-55px TRAINING

slide-30
SLIDE 30

Summary

30

Jan Beneš - On Realism of Architectural Procedural Models

Venice-55px Medieval-55px Paris-55px Favela-55px Venice-37px Medieval-37px Paris-37px Favela-37px TRAINING

slide-31
SLIDE 31

Summary

31

Jan Beneš - On Realism of Architectural Procedural Models

Venice-55px Medieval-55px Paris-55px Favela-55px Venice-37px Medieval-37px Paris-37px Favela-37px Venice-1px Medieval-1px Paris-1px Favela-1px TRAINING

slide-32
SLIDE 32

Summary

32

Jan Beneš - On Realism of Architectural Procedural Models

Venice-55px Medieval-55px Paris-55px Favela-55px Venice-37px Medieval-37px Paris-37px Favela-37px Venice-1px Medieval-1px Paris-1px Favela-1px DEBRIEFING TRAINING

slide-33
SLIDE 33

Data preparation

33

slide-34
SLIDE 34

Photographs

34

Jan Beneš - On Realism of Architectural Procedural Models

slide-35
SLIDE 35

Renders

35

Jan Beneš - On Realism of Architectural Procedural Models

slide-36
SLIDE 36

Data Characteristics

36

Jan Beneš - On Realism of Architectural Procedural Models

300px 300px

slide-37
SLIDE 37

Data Characteristics

37

Jan Beneš - On Realism of Architectural Procedural Models

300px 300px Choose subset

slide-38
SLIDE 38

Quick Peek at Results

38

slide-39
SLIDE 39

Quick Results

39

Jan Beneš - On Realism of Architectural Procedural Models

random choice = 0.5

slide-40
SLIDE 40

Quick Results

40

Jan Beneš - On Realism of Architectural Procedural Models

random choice = 0.5

slide-41
SLIDE 41

Quick Results

41

Jan Beneš - On Realism of Architectural Procedural Models

random choice Favela Best Dataset Medieval Worst Dataset

slide-42
SLIDE 42

Q1: CG vs Real

42

slide-43
SLIDE 43

Q1: CG vs Real

43

Jan Beneš - On Realism of Architectural Procedural Models

  • HDIFF: participants can tell photographs

and generated buildings apart.

– Random choice = 0.5 accuracy – No blur, overall – p<.001 – Can accept HDIFF – Also true for each dataset

  • Also true @ 55px
slide-44
SLIDE 44

Q1: CG vs Real

44

Jan Beneš - On Realism of Architectural Procedural Models

  • HDIFF: participants can tell photographs

and generated buildings apart.

– Random choice = 0.5 accuracy – No blur, overall – p<.001 – Can accept HDIFF – Also true for each dataset

  • Also true @ 55px
slide-45
SLIDE 45

Q2: Details vs Structure

45

slide-46
SLIDE 46

Q2: Details vs Structure

46

Jan Beneš - On Realism of Architectural Procedural Models

  • HSCALE: the detail that allows participants

to tell photographs and generated images apart is present at various scales.

  • ANOVA
slide-47
SLIDE 47

What’s ANOVA?

47

Jan Beneš - On Realism of Architectural Procedural Models

Black box

Independent variable Independent variable Independent variable Dependent variable

slide-48
SLIDE 48

What’s ANOVA?

48

Jan Beneš - On Realism of Architectural Procedural Models

Black box

Blur Size Original image class Dataset Accuracy

slide-49
SLIDE 49

What’s ANOVA?

49

Jan Beneš - On Realism of Architectural Procedural Models

  • ANOVA

– Linear model – Effects of independent variables

slide-50
SLIDE 50

Significant Effects

50

Jan Beneš - On Realism of Architectural Procedural Models

  • Significant effects

– Blur, p<.001 – Dataset, p<.001

  • class, p=.11
  • Blur, p<0.001

=>HSCALE accepted

slide-51
SLIDE 51

HSCALE

51

Jan Beneš - On Realism of Architectural Procedural Models

  • Significant effects

– Blur, p<.001 – Dataset, p<.001

  • Blur, p<.001

=>HSCALE accepted

slide-52
SLIDE 52

More on Blur

52

Jan Beneš - On Realism of Architectural Procedural Models

  • Significant effects

– Blur, p<.001 – Dataset, p<.001

  • Blur, p<.001

=>HSCALE accepted

?

slide-53
SLIDE 53

Post-Hoc - Blur

53

Jan Beneš - On Realism of Architectural Procedural Models

Not significant Significant

slide-54
SLIDE 54

Blurs

54

Jan Beneš - On Realism of Architectural Procedural Models

13px blur 7px blur 1px – no blur 55px blur 32px blur 25px blur

HSCALE: the detail that allows participants to tell photographs and generated images apart is present at various scales.

slide-55
SLIDE 55

Two- & Three-Way Interactions

55

Jan Beneš - On Realism of Architectural Procedural Models

  • Three factors
  • Interactions
  • More in paper
  • Significant
  • Not Significant

Dataset Original Image Class Blur Size

slide-56
SLIDE 56

Q2: Summary

56

Jan Beneš - On Realism of Architectural Procedural Models

  • Blur

– p<.001, significant factor – =>HSCALE accepted – Realism at different scales

  • Exploratory Analysis

– Further insight – Two- & Three-way interactions – Mostly significant

slide-57
SLIDE 57

Q3: What users thought

57

slide-58
SLIDE 58

Participants

58

Jan Beneš - On Realism of Architectural Procedural Models

  • 52 total

– 11 female – 24.3 years old

slide-59
SLIDE 59

What users thought

59

Jan Beneš - On Realism of Architectural Procedural Models

  • Manually tallied debriefings

1. Imperfections & small detail (30/52 ~ 58%) 2. Texture (19/52 ~ 37%) 3. Reflections in windows (18/52 ~ 35%) 4. “Weird” or uniform color (17/52 ~ 33%) 5. Things in & around windows (16/52 ~ 31%) 6. Model Structure (14/52 ~ 27%) 7. Lighting (12/52 ~ 23%) 8. Shadow (12/52 ~ 23%) 9. Regularity (11/52 ~ 21%)

slide-60
SLIDE 60
  • 1. Imperfections & Small Detail

60

Jan Beneš - On Realism of Architectural Procedural Models

  • Imperfections & small detail (30/52 ~ 58%)

Photograph Computer Generated Computer Generated

slide-61
SLIDE 61
  • 2. Texture

61

Jan Beneš - On Realism of Architectural Procedural Models

  • Texture (19/52 ~ 37%)

Computer Generated Computer Generated

slide-62
SLIDE 62
  • 5. Windows

62

Jan Beneš - On Realism of Architectural Procedural Models

  • Things in & around windows (16/52 ~ 31%)

š

Computer Generated Photograph Photograph

slide-63
SLIDE 63
  • 6. Model Structure

63

Jan Beneš - On Realism of Architectural Procedural Models

  • Model Structure (14/52 ~ 27%)

š

Computer Generated Computer Generated

slide-64
SLIDE 64
  • 9. Regularity

64

Jan Beneš - On Realism of Architectural Procedural Models

  • Regularity (11/52 ~ 21%)

š

Computer Generated Computer Generated

slide-65
SLIDE 65

Biases

65

Jan Beneš - On Realism of Architectural Procedural Models

  • Cut-Out Edges

– 21/52 ~ 40% – “played role”

  • Camera Angles

– 18/52 ~35% – Influenced for at least one

  • Background

– 8/52 ~ 15% – Made me choose computer generated more often

slide-66
SLIDE 66

Opinions Summary

66

Jan Beneš - On Realism of Architectural Procedural Models

  • Multi-faceted

– Guidelines, guesses – Not hard facts

  • Biases

Textures Color

slide-67
SLIDE 67

More Exploration

67

slide-68
SLIDE 68

Confounding Buildings @ 55px

68

Jan Beneš - On Realism of Architectural Procedural Models

Computer Generated Photographs

slide-69
SLIDE 69

Summary and Future Work

69

slide-70
SLIDE 70

Summary

70

Jan Beneš - On Realism of Architectural Procedural Models

  • Realism in

– Procedural Modelling – Buildings

  • Methodology for experiment

– Procedural content

  • Verified

– People can tell CG and Photos apart – Realism is carried at different scales

  • “Soft results”

– What people consider – Exploration of results

slide-71
SLIDE 71

Future Work & Limitations

71

Jan Beneš - On Realism of Architectural Procedural Models

  • Future Work

– Understand asset reuse better – Understand importance of structure better – Study buildings in context – Neural networks to automate testing & drive rule generation

  • Limitations

– Design limitations & Biases – Generalization

slide-72
SLIDE 72

Acknowledgements

72

Jan Beneš - On Realism of Architectural Procedural Models

  • ESRI
  • Charles University Grant

SVV-2016-260332

  • Czech Science Foundation

grant 16-18964S.

  • Filip Děchtěrenko was

supported by Czech Academy

  • f Sciences Strategy AV21 –

RVO 68081740

  • vrbn.io
  • Corona Renderer
slide-73
SLIDE 73

Thank You!

73

http://JanBenes.net Supplemental Material

slide-74
SLIDE 74

Biases

74

Jan Beneš - On Realism of Architectural Procedural Models

  • Cut-Out Edges

– 21/52 ~ 40% – “played role”

  • Camera Angles

– 18/52 ~35% – Influenced for at least one

  • Background

– 8/52 ~ 15% – Made me choose computer generated more often

slide-75
SLIDE 75

What users thought

75

Jan Beneš - On Realism of Architectural Procedural Models

  • Manually tallied debriefings

1. Imperfections & small detail (30/52 ~ 58%) 2. Texture (19/52 ~ 37%) 3. Reflections in windows (18/52 ~ 35%) 4. “Weird” or uniform color (17/52 ~ 33%) 5. Things in & around windows (16/52 ~ 31%) 6. Model Structure (14/52 ~ 27%) 7. Lighting (12/52 ~ 23%) 8. Shadow (12/52 ~ 23%) 9. Regularity (11/52 ~ 21%)