SlideShare una empresa de Scribd logo
1 de 53
Pierre BénardJoëlle ThollotGrenoble Universities / INRIA Rhône-AlpesAres Lagae KatholiekeUniversiteit LeuvenREVES - INRIA Sophia-Antipolis Peter VangorpGeorge DrettakisREVES - INRIA Sophia-AntipolisSylvain LefebvreALICE - INRIA Nancy / Loria A Dynamic Noise Primitive for Coherent Stylization
Stylization of 3D Animations 3D scene  2D appearance 2
Stylization of 3D Animations 3D scene  2D appearance Stylized color regions 2D medium: a pattern Temporal coherence 3 Paint strokes Pencil strokes Paper Watercolor pigments
Hand–made animation « Il pleut bergère », Jérémy Depuydt (2005) 4 PoppingTemporal continuity
Naïve CG solutions 5 Shower-door effect  Coherent Motion Traditional mapping  Flatness
Temporal Coherence Problem Extreme cases  Requirements 6 Flatness Shower-door Popping Coherent motion Temporal continuity Traditional mapping Contradictory requirements: solution  find a compromise
3 goals to ensure at best Additional challenges Flexibility 		 	variety of styles Interactivity 	 	artistic control Evaluation  		 	quality of the trade-off Flatness Coherent motion Temporal continuity 7
Previous Work
Texture-Based methods Object-space ,[object Object]
Perspective distortionFlatness [BBT09] Popping Shower-door Coherent motion Temporal continuity Object-space texture mapping[KLK*00,PHWF01,FMS01,BBT09] Traditional mapping 9
Texture-Based methods Object-space Screen-space ,[object Object],Flatness Screen-space texture mapping[CTP*03,CDH06,BSM*07,BNTS07] Popping [CTP*03] Coherent motion Temporal continuity Object-space texture mapping[KLK*00,PHWF01,FMS01,BBT09] 10 Shower-door
Few-Primitive methods ,[object Object]
Popping11 or Flatness [Mei96] Few-primitive methods [Mei96,Dan99,HE04,VBTS07] Screen-space texture mapping[CTP*03,CDH06,BSM*07,BNTS07] Popping Coherent motion Temporal continuity Object-space texture mapping[KLK*00,PHWF01,FMS01,BBT09]
Few-Primitive methods 12 Vanderhaeghe et al. EGSR 2007
Key Insight Blending a large number of primitives Reduce popping artifacts Individual primitives merge  texture 13
Many-Primitive methods [KC05] Flatness Few-primitive methods [Mei96,Dan99,HE04,VBTS07] Screen-space texture mapping[CTP*03,CDH06,BSM*07,BNTS07] Many-primitive methods[KC05,BKTS06] Coherent motion Temporal continuity 14 Object-space texture mapping[KLK*00,PHWF01,FMS01,BBT09]
NPR Gabor Noise
Procedural noises Sparse convolution [Lewis 84,89] Spot Noise [van Wijk 91] Gabor Noise [LLDD09]  Our trade-off: NPR Gabor Noise 16
Gabor Noise [LLDD09] Offers significant spectral control Support anisotropy Is fast to evaluate 17 See “State of the Art in Procedural Noise Functions”, EG 2010 for comparisons with previous work
Gabor Noise [LLDD09] Definition Sum of randomly positioned and weighted kernels 18 Gabor kernel noise random positionsand weights
NPR Gabor Noise Basic principles follow from the goals Flatness ,[object Object]
 Evaluation in 2D screen space19 2D Gabor noise [LLDD09]
NPR Gabor Noise Basic principles follow from the goals Flatness Coherent motion ,[object Object],20 Surface Gabor noise [LLDD09] 2D Gabor noise [LLDD09]
NPR Gabor Noise Basic principles follow from the goals Flatness Coherent motion 21 Surface Gabor noise [LLDD09] NPR Gabor noise 2D Gabor noise [LLDD09]
NPR Gabor Noise Basic principles follow from the goals Flatness Coherent motion Continuity ,[object Object],22 Surface Gabor noise [LLDD09] NPR Gabor noise 2D Gabor noise [LLDD09]
GPU Splatting Algorithm Sample 3D triangles 2D Poisson distribution with constant screen space density PRNG: seed = triangle ID 23 Far ,[object Object]
less pointsClose ,[object Object]
more points,[object Object]
LOD Mechanism Blending scheme using statistical properties Reduce popping Preserve noise appearance 25
Styles
Style Design Standard techniques from procedural texturing and modeling [EMPPW02] Threshold  Smooth step function  X-toon textures [BTM06] Compositing (alpha-blending, overlay) Local control Curvature  noise orientation Shading  noise frequency Interactivefeedback Threshold texture 27
Style Design 28
Results: 29 isotropic as well asanisotropic patterns
30 local variation	according to shading Results:
31 local orientation guided 	  by surface curvature Results:
User Study
User Study: Motivation Evaluate success of various solutions according to Relative importance of these criteria 33 Flatness Coherent motion Temporal continuity
User Study: Setup Methodology 15 naïve subjects, ~ 20-30 minutes Ranking tasks “Rank the images/videos according to … ” 34
User Study: Compared methods 35 Local screen-space Global screen-space Object-space Adv D2D DST ours SD TM Extreme cases
User Study: Flatness Adv D2D DST ours SD TM Simple stimuli 36 Object-space
User Study: Flatness Complex stimuli Adv D2D DST ours SD TM 37
User Study: Flatness “Rank the images according to how flat they appear.” Simple stimuli ,[object Object]
Object-space methods less flatComplex stimuli ,[object Object]
 Many 3D cues  flatness not perceived38
Simple stimuli User Study: Dynamic stimuli 39
Complex stimuli User Study: Dynamic stimuli 40
User Study: Coherent motion “Rank the videos according to how coherently the pattern moves with the object.” Simple stimuli ,[object Object]
Shower-door least coherent
Image-space methods provide a tradeoffComplex stimuli ,[object Object]
Our approach slightly betterthan other image-space methods41
“Rank the videos according to how much the pattern changes over time.” Simple stimuli ,[object Object]
Advection and ours produce more changes
 “swimming” artifactsComplex stimuli ,[object Object]

Más contenido relacionado

La actualidad más candente

elsevier_publication_2013
elsevier_publication_2013elsevier_publication_2013
elsevier_publication_2013pranay yadav
 
impulse noise filter
impulse noise filter impulse noise filter
impulse noise filter yousef_
 
Noise reduction by fuzzy image filtering(synopsis)
Noise reduction by fuzzy image filtering(synopsis)Noise reduction by fuzzy image filtering(synopsis)
Noise reduction by fuzzy image filtering(synopsis)Mumbai Academisc
 
23 an investigation on image 233 241
23 an investigation on image 233 24123 an investigation on image 233 241
23 an investigation on image 233 241Alexander Decker
 
Removal of Salt and Pepper Noise in images
Removal of Salt and Pepper Noise in imagesRemoval of Salt and Pepper Noise in images
Removal of Salt and Pepper Noise in imagesMurali Siva
 
Speckle Noise Reduction in Ultrasound Images using Adaptive and Anisotropic D...
Speckle Noise Reduction in Ultrasound Images using Adaptive and Anisotropic D...Speckle Noise Reduction in Ultrasound Images using Adaptive and Anisotropic D...
Speckle Noise Reduction in Ultrasound Images using Adaptive and Anisotropic D...Md. Shohel Rana
 
Beyond screens presentation web
Beyond screens presentation webBeyond screens presentation web
Beyond screens presentation webJun Hu
 
Performance Comparison of Various Filters and Wavelet Transform for Image De-...
Performance Comparison of Various Filters and Wavelet Transform for Image De-...Performance Comparison of Various Filters and Wavelet Transform for Image De-...
Performance Comparison of Various Filters and Wavelet Transform for Image De-...IOSR Journals
 
Paper id 28201452
Paper id 28201452Paper id 28201452
Paper id 28201452IJRAT
 
An overview of the fundamental approaches that yield several image denoising ...
An overview of the fundamental approaches that yield several image denoising ...An overview of the fundamental approaches that yield several image denoising ...
An overview of the fundamental approaches that yield several image denoising ...TELKOMNIKA JOURNAL
 

La actualidad más candente (15)

NOISE FILTERS IN IMAGE PROCESSING
NOISE FILTERS IN IMAGE PROCESSINGNOISE FILTERS IN IMAGE PROCESSING
NOISE FILTERS IN IMAGE PROCESSING
 
elsevier_publication_2013
elsevier_publication_2013elsevier_publication_2013
elsevier_publication_2013
 
impulse noise filter
impulse noise filter impulse noise filter
impulse noise filter
 
PID3474431
PID3474431PID3474431
PID3474431
 
Image Filtering
Image FilteringImage Filtering
Image Filtering
 
Noise reduction by fuzzy image filtering(synopsis)
Noise reduction by fuzzy image filtering(synopsis)Noise reduction by fuzzy image filtering(synopsis)
Noise reduction by fuzzy image filtering(synopsis)
 
Chapter01 (2)
Chapter01 (2)Chapter01 (2)
Chapter01 (2)
 
23 an investigation on image 233 241
23 an investigation on image 233 24123 an investigation on image 233 241
23 an investigation on image 233 241
 
Removal of Salt and Pepper Noise in images
Removal of Salt and Pepper Noise in imagesRemoval of Salt and Pepper Noise in images
Removal of Salt and Pepper Noise in images
 
Speckle Noise Reduction in Ultrasound Images using Adaptive and Anisotropic D...
Speckle Noise Reduction in Ultrasound Images using Adaptive and Anisotropic D...Speckle Noise Reduction in Ultrasound Images using Adaptive and Anisotropic D...
Speckle Noise Reduction in Ultrasound Images using Adaptive and Anisotropic D...
 
Beyond screens presentation web
Beyond screens presentation webBeyond screens presentation web
Beyond screens presentation web
 
Chap01 visual perception
Chap01 visual perceptionChap01 visual perception
Chap01 visual perception
 
Performance Comparison of Various Filters and Wavelet Transform for Image De-...
Performance Comparison of Various Filters and Wavelet Transform for Image De-...Performance Comparison of Various Filters and Wavelet Transform for Image De-...
Performance Comparison of Various Filters and Wavelet Transform for Image De-...
 
Paper id 28201452
Paper id 28201452Paper id 28201452
Paper id 28201452
 
An overview of the fundamental approaches that yield several image denoising ...
An overview of the fundamental approaches that yield several image denoising ...An overview of the fundamental approaches that yield several image denoising ...
An overview of the fundamental approaches that yield several image denoising ...
 

Similar a A Dynamic Noise Primitive for Coherent Stylization, EGSR 2010

Pierre Bénard Ph.D. defense, 2011/07/07
Pierre Bénard Ph.D. defense, 2011/07/07Pierre Bénard Ph.D. defense, 2011/07/07
Pierre Bénard Ph.D. defense, 2011/07/07Pierre Bénard
 
Relief: A Modeling By Drawing Tool
Relief: A Modeling By Drawing ToolRelief: A Modeling By Drawing Tool
Relief: A Modeling By Drawing ToolDavid Bourguignon
 
Montage4D: Interactive Seamless Fusion of Multiview Video Textures
Montage4D: Interactive Seamless Fusion of Multiview Video TexturesMontage4D: Interactive Seamless Fusion of Multiview Video Textures
Montage4D: Interactive Seamless Fusion of Multiview Video TexturesRuofei Du
 
Paris_06_3D_Reconstruction (1).ppt
Paris_06_3D_Reconstruction (1).pptParis_06_3D_Reconstruction (1).ppt
Paris_06_3D_Reconstruction (1).pptTANAJI KAMBLE
 
Real-Time Volumetric Tests (EG 2008)
Real-Time Volumetric Tests (EG 2008)Real-Time Volumetric Tests (EG 2008)
Real-Time Volumetric Tests (EG 2008)Matthias Trapp
 
Evaluating the Perceptual Impact of Rendering Techniques on Thematic Color Ma...
Evaluating the Perceptual Impact of Rendering Techniques on Thematic Color Ma...Evaluating the Perceptual Impact of Rendering Techniques on Thematic Color Ma...
Evaluating the Perceptual Impact of Rendering Techniques on Thematic Color Ma...Matthias Trapp
 
Drawing For Illustration And Annotation In 3D
Drawing For Illustration And Annotation In 3DDrawing For Illustration And Annotation In 3D
Drawing For Illustration And Annotation In 3DDavid Bourguignon
 
2014 12-22 - open 3 d printing and fabrication technology (cd)
2014 12-22 - open 3 d printing and fabrication technology (cd)2014 12-22 - open 3 d printing and fabrication technology (cd)
2014 12-22 - open 3 d printing and fabrication technology (cd)FabLab Pisa
 
Introduction to Binocular Stereo in Computer Vision
Introduction to Binocular Stereo in Computer VisionIntroduction to Binocular Stereo in Computer Vision
Introduction to Binocular Stereo in Computer Visionothersk46
 
Dense Image Matching - Challenges and Potentials (Keynote 3D-ARCH 2015)
Dense Image Matching - Challenges and Potentials (Keynote 3D-ARCH 2015) Dense Image Matching - Challenges and Potentials (Keynote 3D-ARCH 2015)
Dense Image Matching - Challenges and Potentials (Keynote 3D-ARCH 2015) Konrad Wenzel
 
Dissertation synopsis for imagedenoising(noise reduction )using non local me...
Dissertation synopsis for  imagedenoising(noise reduction )using non local me...Dissertation synopsis for  imagedenoising(noise reduction )using non local me...
Dissertation synopsis for imagedenoising(noise reduction )using non local me...Arti Singh
 
Interactive Stereoscopic Rendering for Non-Planar Projections (GRAPP 2009)
Interactive Stereoscopic Rendering for Non-Planar Projections (GRAPP 2009)Interactive Stereoscopic Rendering for Non-Planar Projections (GRAPP 2009)
Interactive Stereoscopic Rendering for Non-Planar Projections (GRAPP 2009)Matthias Trapp
 
ColorBless: Augmenting Visual Information for Colorblind People with Binocula...
ColorBless: Augmenting Visual Information for Colorblind People with Binocula...ColorBless: Augmenting Visual Information for Colorblind People with Binocula...
ColorBless: Augmenting Visual Information for Colorblind People with Binocula...Soon Hau Chua
 
AUTOMATIC DESIGN OF COLOR FILTER ARRAYS IN THE FREQUENCY DOMAIN
AUTOMATIC DESIGN OF COLOR FILTER ARRAYS IN THE FREQUENCY DOMAINAUTOMATIC DESIGN OF COLOR FILTER ARRAYS IN THE FREQUENCY DOMAIN
AUTOMATIC DESIGN OF COLOR FILTER ARRAYS IN THE FREQUENCY DOMAINNexgen Technology
 
3D Acquisition and Modeling in Cultural Heritage
3D Acquisition and Modeling in Cultural Heritage3D Acquisition and Modeling in Cultural Heritage
3D Acquisition and Modeling in Cultural HeritageGabriele Guidi
 
Image Restoration Using Particle Filters By Improving The Scale Of Texture Wi...
Image Restoration Using Particle Filters By Improving The Scale Of Texture Wi...Image Restoration Using Particle Filters By Improving The Scale Of Texture Wi...
Image Restoration Using Particle Filters By Improving The Scale Of Texture Wi...CSCJournals
 

Similar a A Dynamic Noise Primitive for Coherent Stylization, EGSR 2010 (20)

Pierre Bénard Ph.D. defense, 2011/07/07
Pierre Bénard Ph.D. defense, 2011/07/07Pierre Bénard Ph.D. defense, 2011/07/07
Pierre Bénard Ph.D. defense, 2011/07/07
 
Relief: A Modeling By Drawing Tool
Relief: A Modeling By Drawing ToolRelief: A Modeling By Drawing Tool
Relief: A Modeling By Drawing Tool
 
Montage4D: Interactive Seamless Fusion of Multiview Video Textures
Montage4D: Interactive Seamless Fusion of Multiview Video TexturesMontage4D: Interactive Seamless Fusion of Multiview Video Textures
Montage4D: Interactive Seamless Fusion of Multiview Video Textures
 
Paris_06_3D_Reconstruction (1).ppt
Paris_06_3D_Reconstruction (1).pptParis_06_3D_Reconstruction (1).ppt
Paris_06_3D_Reconstruction (1).ppt
 
Real-Time Volumetric Tests (EG 2008)
Real-Time Volumetric Tests (EG 2008)Real-Time Volumetric Tests (EG 2008)
Real-Time Volumetric Tests (EG 2008)
 
DoE applied on visual appearance of materials
DoE applied on visual appearance of materialsDoE applied on visual appearance of materials
DoE applied on visual appearance of materials
 
Pro active management of visual appearance of products
Pro active management of visual appearance of productsPro active management of visual appearance of products
Pro active management of visual appearance of products
 
Evaluating the Perceptual Impact of Rendering Techniques on Thematic Color Ma...
Evaluating the Perceptual Impact of Rendering Techniques on Thematic Color Ma...Evaluating the Perceptual Impact of Rendering Techniques on Thematic Color Ma...
Evaluating the Perceptual Impact of Rendering Techniques on Thematic Color Ma...
 
Drawing For Illustration And Annotation In 3D
Drawing For Illustration And Annotation In 3DDrawing For Illustration And Annotation In 3D
Drawing For Illustration And Annotation In 3D
 
2014 12-22 - open 3 d printing and fabrication technology (cd)
2014 12-22 - open 3 d printing and fabrication technology (cd)2014 12-22 - open 3 d printing and fabrication technology (cd)
2014 12-22 - open 3 d printing and fabrication technology (cd)
 
Introduction to Binocular Stereo in Computer Vision
Introduction to Binocular Stereo in Computer VisionIntroduction to Binocular Stereo in Computer Vision
Introduction to Binocular Stereo in Computer Vision
 
Dense Image Matching - Challenges and Potentials (Keynote 3D-ARCH 2015)
Dense Image Matching - Challenges and Potentials (Keynote 3D-ARCH 2015) Dense Image Matching - Challenges and Potentials (Keynote 3D-ARCH 2015)
Dense Image Matching - Challenges and Potentials (Keynote 3D-ARCH 2015)
 
Dissertation synopsis for imagedenoising(noise reduction )using non local me...
Dissertation synopsis for  imagedenoising(noise reduction )using non local me...Dissertation synopsis for  imagedenoising(noise reduction )using non local me...
Dissertation synopsis for imagedenoising(noise reduction )using non local me...
 
Interactive Stereoscopic Rendering for Non-Planar Projections (GRAPP 2009)
Interactive Stereoscopic Rendering for Non-Planar Projections (GRAPP 2009)Interactive Stereoscopic Rendering for Non-Planar Projections (GRAPP 2009)
Interactive Stereoscopic Rendering for Non-Planar Projections (GRAPP 2009)
 
ColorBless: Augmenting Visual Information for Colorblind People with Binocula...
ColorBless: Augmenting Visual Information for Colorblind People with Binocula...ColorBless: Augmenting Visual Information for Colorblind People with Binocula...
ColorBless: Augmenting Visual Information for Colorblind People with Binocula...
 
AUTOMATIC DESIGN OF COLOR FILTER ARRAYS IN THE FREQUENCY DOMAIN
AUTOMATIC DESIGN OF COLOR FILTER ARRAYS IN THE FREQUENCY DOMAINAUTOMATIC DESIGN OF COLOR FILTER ARRAYS IN THE FREQUENCY DOMAIN
AUTOMATIC DESIGN OF COLOR FILTER ARRAYS IN THE FREQUENCY DOMAIN
 
3D Acquisition and Modeling in Cultural Heritage
3D Acquisition and Modeling in Cultural Heritage3D Acquisition and Modeling in Cultural Heritage
3D Acquisition and Modeling in Cultural Heritage
 
3 D texturing
 3 D texturing 3 D texturing
3 D texturing
 
surveillance.ppt
surveillance.pptsurveillance.ppt
surveillance.ppt
 
Image Restoration Using Particle Filters By Improving The Scale Of Texture Wi...
Image Restoration Using Particle Filters By Improving The Scale Of Texture Wi...Image Restoration Using Particle Filters By Improving The Scale Of Texture Wi...
Image Restoration Using Particle Filters By Improving The Scale Of Texture Wi...
 

Último

[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdfSandro Moreira
 
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Angeliki Cooney
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsNanddeep Nachan
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Orbitshub
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024The Digital Insurer
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWERMadyBayot
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxRustici Software
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProduct Anonymous
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Victor Rentea
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyKhushali Kathiriya
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...apidays
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...apidays
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherRemote DBA Services
 
Six Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal OntologySix Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal Ontologyjohnbeverley2021
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...apidays
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAndrey Devyatkin
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century educationjfdjdjcjdnsjd
 

Último (20)

[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
 
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectors
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Six Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal OntologySix Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal Ontology
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 

A Dynamic Noise Primitive for Coherent Stylization, EGSR 2010

  • 1. Pierre BénardJoëlle ThollotGrenoble Universities / INRIA Rhône-AlpesAres Lagae KatholiekeUniversiteit LeuvenREVES - INRIA Sophia-Antipolis Peter VangorpGeorge DrettakisREVES - INRIA Sophia-AntipolisSylvain LefebvreALICE - INRIA Nancy / Loria A Dynamic Noise Primitive for Coherent Stylization
  • 2. Stylization of 3D Animations 3D scene  2D appearance 2
  • 3. Stylization of 3D Animations 3D scene  2D appearance Stylized color regions 2D medium: a pattern Temporal coherence 3 Paint strokes Pencil strokes Paper Watercolor pigments
  • 4. Hand–made animation « Il pleut bergère », Jérémy Depuydt (2005) 4 PoppingTemporal continuity
  • 5. Naïve CG solutions 5 Shower-door effect  Coherent Motion Traditional mapping  Flatness
  • 6. Temporal Coherence Problem Extreme cases  Requirements 6 Flatness Shower-door Popping Coherent motion Temporal continuity Traditional mapping Contradictory requirements: solution  find a compromise
  • 7. 3 goals to ensure at best Additional challenges Flexibility  variety of styles Interactivity  artistic control Evaluation  quality of the trade-off Flatness Coherent motion Temporal continuity 7
  • 9.
  • 10. Perspective distortionFlatness [BBT09] Popping Shower-door Coherent motion Temporal continuity Object-space texture mapping[KLK*00,PHWF01,FMS01,BBT09] Traditional mapping 9
  • 11.
  • 12.
  • 13. Popping11 or Flatness [Mei96] Few-primitive methods [Mei96,Dan99,HE04,VBTS07] Screen-space texture mapping[CTP*03,CDH06,BSM*07,BNTS07] Popping Coherent motion Temporal continuity Object-space texture mapping[KLK*00,PHWF01,FMS01,BBT09]
  • 14. Few-Primitive methods 12 Vanderhaeghe et al. EGSR 2007
  • 15. Key Insight Blending a large number of primitives Reduce popping artifacts Individual primitives merge  texture 13
  • 16. Many-Primitive methods [KC05] Flatness Few-primitive methods [Mei96,Dan99,HE04,VBTS07] Screen-space texture mapping[CTP*03,CDH06,BSM*07,BNTS07] Many-primitive methods[KC05,BKTS06] Coherent motion Temporal continuity 14 Object-space texture mapping[KLK*00,PHWF01,FMS01,BBT09]
  • 18. Procedural noises Sparse convolution [Lewis 84,89] Spot Noise [van Wijk 91] Gabor Noise [LLDD09]  Our trade-off: NPR Gabor Noise 16
  • 19. Gabor Noise [LLDD09] Offers significant spectral control Support anisotropy Is fast to evaluate 17 See “State of the Art in Procedural Noise Functions”, EG 2010 for comparisons with previous work
  • 20. Gabor Noise [LLDD09] Definition Sum of randomly positioned and weighted kernels 18 Gabor kernel noise random positionsand weights
  • 21.
  • 22. Evaluation in 2D screen space19 2D Gabor noise [LLDD09]
  • 23.
  • 24. NPR Gabor Noise Basic principles follow from the goals Flatness Coherent motion 21 Surface Gabor noise [LLDD09] NPR Gabor noise 2D Gabor noise [LLDD09]
  • 25.
  • 26.
  • 27.
  • 28.
  • 29. LOD Mechanism Blending scheme using statistical properties Reduce popping Preserve noise appearance 25
  • 31. Style Design Standard techniques from procedural texturing and modeling [EMPPW02] Threshold Smooth step function X-toon textures [BTM06] Compositing (alpha-blending, overlay) Local control Curvature  noise orientation Shading  noise frequency Interactivefeedback Threshold texture 27
  • 33. Results: 29 isotropic as well asanisotropic patterns
  • 34. 30 local variation according to shading Results:
  • 35. 31 local orientation guided by surface curvature Results:
  • 37. User Study: Motivation Evaluate success of various solutions according to Relative importance of these criteria 33 Flatness Coherent motion Temporal continuity
  • 38. User Study: Setup Methodology 15 naïve subjects, ~ 20-30 minutes Ranking tasks “Rank the images/videos according to … ” 34
  • 39. User Study: Compared methods 35 Local screen-space Global screen-space Object-space Adv D2D DST ours SD TM Extreme cases
  • 40. User Study: Flatness Adv D2D DST ours SD TM Simple stimuli 36 Object-space
  • 41. User Study: Flatness Complex stimuli Adv D2D DST ours SD TM 37
  • 42.
  • 43.
  • 44. Many 3D cues  flatness not perceived38
  • 45. Simple stimuli User Study: Dynamic stimuli 39
  • 46. Complex stimuli User Study: Dynamic stimuli 40
  • 47.
  • 49.
  • 50. Our approach slightly betterthan other image-space methods41
  • 51.
  • 52. Advection and ours produce more changes
  • 53.
  • 54. Others perceived equallyUser Study: Temporal continuity 42
  • 55.
  • 57.
  • 59.
  • 60. Flatness hard to see in complex scenes
  • 61. Motion coherence predominant criteriaIntrinsic limitations Hatching  other styles Naïve users  professional artists Objective metric Statistical texture measures [BTS09] Optical flow analysis 46
  • 62.
  • 63.
  • 65.
  • 66. User Study: Flatness “Rank the images according to how flat they appear.” Simple stimuli Complex stimuli less flat more flat less flat more flat 50 50
  • 67. User Study: Coherent motion “Rank the videos according to how coherently the pattern moves with the object.” Simple stimuli Complex stimuli Object-space translate: rotate: zoom: more coherent less coherent less coherent more coherent 51
  • 68. “Rank the videos according to how much the pattern changes over time.” Simple stimuli Complex stimuli User Study: Temporal continuity translate: rotate: zoom: more change less change more change less change 52 52
  • 69. User Study: Pleasantness “Rank the videos according to how pleasant you find them in the context of cartoon animation.” Complex stimuli Object-space less pleasant more pleasant 80 53

Notas del editor

  1. In complement to our analysis of previous work on the triangle of requirements, we would like to evaluate how final viewers actually perceive these tradeoffs. We believe that such study can provide significant insight into how well previous solutions, including ours, perform for each goal: flatness: how much is the pattern perceived as produced in 2D coherent motion: how closely is the pattern following the 3D motion of the scene and temporal continuity: how much does the pattern change over timeBesides, this study may give an indication of the relative importance of these criteria. That is if the choice of an equilateral triangle is meaningful.
  2. The results for motion coherence and pleasantness exhibits least variance and are strongly correlated.This indicates that motion coherence is probably the most important quality to preserve in the overall temporal coherence compromise.Both Dynamic Solid Textures and our method perform well on the motion coherence scale: the first one trades off better temporal continuity, whereas ours trades off better flatness.