architectural procedural models
play

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


  1. On Realism of Architectural Procedural Models Jan Bene š, Tom Kelly, Filip Děchtěrenko , Jaroslav Křivánek, Pascal Müller

  2. Quick Quiz 2 Jan Bene š - On Realism of Architectural Procedural Models

  3. Quick Quiz Computer Generated Photograph 3 Jan Bene š - On Realism of Architectural Procedural Models

  4. Overview Experiment Procedural Modeling Answers & & Data Acquisition Realism Questions Previous Work 4 Jan Bene š - On Realism of Architectural Procedural Models

  5. Procedural Modeling • Procedural modeling – Tool for artists [Palubicki09] – Or fully automatic – Wide range of outputs • Wide use [Independence Day] 5 Jan Bene š - On Realism of Architectural Procedural Models

  6. Procedural Modeling • Procedural modeling – Tool for artists [Palubicki09] – Or fully automatic – Wide range of outputs • Wide use [Independence Day] 6 Jan Bene š - On Realism of Architectural Procedural Models

  7. Realism Realism  Plausibility  Immersion • Model & material & display • Should be studied • For procedural modelling [Velocipedia, Gianluca Gimini] 7 Jan Bene š - On Realism of Architectural Procedural Models

  8. Realism Realism  Plausibility  Immersion • Model & material & display • Should be studied • For procedural modelling [Velocipedia, Gianluca Gimini] 8 Jan Bene š - On Realism of Architectural Procedural Models

  9. What we did Procedural architecture 9 Jan Bene š - On Realism of Architectural Procedural Models

  10. What we did User Study 10 Jan Bene š - On Realism of Architectural Procedural Models

  11. Question #1 (1) Can people tell procedurally generated buildings from real ones? 11 Jan Bene š - On Realism of Architectural Procedural Models

  12. Question #2 (2) Is realism carried in the detail or in the larger structure? 12 Jan Bene š - On Realism of Architectural Procedural Models

  13. Question #2 (2) Is realism carried in the detail or in the larger structure? 13 Jan Bene š - On Realism of Architectural Procedural Models

  14. Question #2 (2) Is realism carried in the detail or in the larger structure? 14 Jan Bene š - On Realism of Architectural Procedural Models

  15. Question #3 I think… (3) What factors do the users think influence the perception of realism? 15 Jan Bene š - On Realism of Architectural Procedural Models

  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 I think… think influence the perception of realism? 16 Jan Bene š - On Realism of Architectural Procedural Models

  17. Previous Work 17

  18. Previous Work - Realism “There is no dirt, no dust, no fingerprints on the glass table…simply too beautiful, too clean and polished…” [Reinhard13] 18 Jan Bene š - On Realism of Architectural Procedural Models

  19. Previous Work - Realism CG2Real [Johnson11] 19 Jan Bene š - On Realism of Architectural Procedural Models

  20. Previous Work - Realism [Rademacher01] 20 Jan Bene š - On Realism of Architectural Procedural Models

  21. Previous Work - Buildings • Building generation – Grammar [Stiny80, Wonka03, Muller06, Schwarz15] – Data [Fan16] – Sketch [Nishida16] – Predefined parts [Kalogerakis12, Talton12] 21 Jan Bene š - On Realism of Architectural Procedural Models

  22. Previous Work - Miscellaneous • 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] 22 Jan Bene š - On Realism of Architectural Procedural Models

  23. Experimental Setup 23

  24. Datasets Favela Medieval Paris Venice 24 Jan Bene š - On Realism of Architectural Procedural Models

  25. Datasets Computer Generated Photos Venice Favela Medieval Paris 25 Jan Bene š - On Realism of Architectural Procedural Models

  26. Classification Screen X X 26 Jan Bene š - On Realism of Architectural Procedural Models

  27. Blurs 1px – no blur 7px blur 13px blur 55px blur 25px blur 32px blur 27 Jan Bene š - On Realism of Architectural Procedural Models

  28. Summary TRAINING 28 Jan Bene š - On Realism of Architectural Procedural Models

  29. Summary TRAINING Venice-55px Medieval-55px Paris-55px Favela-55px 29 Jan Bene š - On Realism of Architectural Procedural Models

  30. Summary TRAINING Venice-55px Venice-37px Medieval-55px Medieval-37px Paris-55px Paris-37px Favela-55px Favela-37px 30 Jan Bene š - On Realism of Architectural Procedural Models

  31. Summary TRAINING Venice-1px Venice-55px Venice-37px … Medieval-55px Medieval-1px Medieval-37px Paris-1px Paris-55px Paris-37px Favela-55px Favela-37px Favela-1px 31 Jan Bene š - On Realism of Architectural Procedural Models

  32. Summary TRAINING Venice-1px Venice-55px Venice-37px … Medieval-55px Medieval-1px Medieval-37px Paris-1px Paris-55px Paris-37px Favela-55px Favela-37px Favela-1px DEBRIEFING 32 Jan Bene š - On Realism of Architectural Procedural Models

  33. Data preparation 33

  34. Photographs 34 Jan Bene š - On Realism of Architectural Procedural Models

  35. Renders 35 Jan Bene š - On Realism of Architectural Procedural Models

  36. Data Characteristics 300px 300px 36 Jan Bene š - On Realism of Architectural Procedural Models

  37. Data Characteristics 300px Choose subset 300px 37 Jan Bene š - On Realism of Architectural Procedural Models

  38. Quick Peek at Results 38

  39. Quick Results random choice = 0.5 39 Jan Bene š - On Realism of Architectural Procedural Models

  40. Quick Results random choice = 0.5 40 Jan Bene š - On Realism of Architectural Procedural Models

  41. Quick Results Medieval Worst Dataset random choice Favela Best Dataset 41 Jan Bene š - On Realism of Architectural Procedural Models

  42. Q1: CG vs Real 42

  43. Q1: CG vs Real • H DIFF : participants can tell photographs and generated buildings apart. – Random choice = 0.5 accuracy – No blur, overall – p <.001 – Can accept H DIFF – Also true for each dataset • Also true @ 55px 43 Jan Bene š - On Realism of Architectural Procedural Models

  44. Q1: CG vs Real • H DIFF : participants can tell photographs and generated buildings apart. – Random choice = 0.5 accuracy – No blur, overall – p <.001 – Can accept H DIFF – Also true for each dataset • Also true @ 55px 44 Jan Bene š - On Realism of Architectural Procedural Models

  45. Q2: Details vs Structure 45

  46. Q2: Details vs Structure • H SCALE : the detail that allows participants to tell photographs and generated images apart is present at various scales. • ANOVA 46 Jan Bene š - On Realism of Architectural Procedural Models

  47. What’s ANOVA? Independent variable Independent Dependent Black box variable variable Independent variable 47 Jan Bene š - On Realism of Architectural Procedural Models

  48. What’s ANOVA? Blur Size Original Black box Accuracy image class Dataset 48 Jan Bene š - On Realism of Architectural Procedural Models

  49. What’s ANOVA? • ANOVA – Linear model – Effects of independent variables 49 Jan Bene š - On Realism of Architectural Procedural Models

  50. Significant Effects • Significant effects – Blur, p <.001 – Dataset, p <.001 • class, p =.11 • Blur, p <0.001 =>H SCALE accepted 50 Jan Bene š - On Realism of Architectural Procedural Models

  51. H SCALE • Significant effects – Blur, p <.001 – Dataset, p <.001 • Blur, p <.001 =>H SCALE accepted 51 Jan Bene š - On Realism of Architectural Procedural Models

  52. More on Blur • Significant effects ? – Blur, p <.001 – Dataset, p <.001 • Blur, p <.001 =>H SCALE accepted 52 Jan Bene š - On Realism of Architectural Procedural Models

  53. Post-Hoc - Blur Significant Not significant 53 Jan Bene š - On Realism of Architectural Procedural Models

  54. Blurs 1px – no blur 7px blur 13px blur 25px blur 32px blur 55px blur H SCALE : the detail that allows participants to tell photographs and generated images apart is present at various scales. 54 Jan Bene š - On Realism of Architectural Procedural Models

  55. Two- & Three-Way Interactions Blur Size • Three factors • Interactions • More in paper • Significant • Not Significant Original Image Class Dataset 55 Jan Bene š - On Realism of Architectural Procedural Models

  56. Q2: Summary • Blur – p <.001, significant factor – =>H SCALE accepted – Realism at different scales • Exploratory Analysis – Further insight – Two- & Three-way interactions – Mostly significant 56 Jan Bene š - On Realism of Architectural Procedural Models

  57. Q3: What users thought 57

  58. Participants • 52 total – 11 female – 24.3 years old 58 Jan Bene š - On Realism of Architectural Procedural Models

Recommend


More recommend