Daniel Berio - Graffiti synthesis, a motion centric approach - Creative AI meetup

Luba Elliott
Luba ElliottAI Curator
Autograff
Optimality Principles
in the Procedural Generation of Graffiti Style
Graffiti synthesis, a motion centric approach
Daniel Berio
http://doc.gold.ac.uk/autograf
@colormotor
Graffiti art
Graffiti art
Graffiti – canvas in motion
Graffiti art - tags
• Elementary “Atom” of graffiti art
• Highly stylized signature denoting an artist’s pseudonym
• Generated by rapidly executed and well learned movements
– Different style are referred to as “hand styles”
– In graffiti jargon, a well made tag has ”flow”
Embodied perception
• Well known relations between kinematics and geometry of human movements
(e.g. power laws) (Lacquaniti et al. 1983)
• Observation of a human made trace triggers the mental recovery of the
movement underlying its production
(Freedberg and Gallese 2007, Longcamp et al. 2006, Pignocchi 2010)
• Such recovery influences aesthetic appreciation (Leder et al. 2012)
Embodied perception
• Well known relations between kinematics and geometry of human movements
(e.g. power laws) (Lacquaniti et al. 1983)
• Observation of a human made trace triggers the mental recovery of the
movement underlying its production
(Freedberg and Gallese 2007, Longcamp et al. 2006, Pignocchi 2010)
• Such recovery influences aesthetic appreciation (Leder et al. 2012)
• It follows that an appropriate simulation of movement may trigger a similar
effect in the viewer for computer generated traces.
Graffiti Taxonomy
Evan Roth, Graffiti Taxonomy https://www.moma.org/collection/works/147174
Common letter structure
Bi-level representation of “style”
Movement centric curve generation
Trajectory formation model Stylized trajectoriesControl polygon / motor plan
Parameters ?
Data driven approach
Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon
Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO
Trajectory formation model Stylized trajectoriesStructure (motor plan)
Graphonomics
The scientific field ”concerned with the systematic
relationships involved in the generation and analysis of the
handwriting and drawing movements, and the resulting
traces of writing and drawing instruments”
(Kao, Hoosain, & Van Galen, 1986)
Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon
Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO
Graphonomics - principles
• Aiming movements assume a “bell shaped” speed profile (Morasso, 1981)
• Handwriting movements can be decomposed into a discrete number of
aiming movement primitives (strokes)
(Teulings and Schomaker 1993, Mussa Ivaldi and Solla 2004, Sosnik et al. 2004, Plamondon et al. 2014)
– Also characterized by the same bell shaped speed profile.
– Each stroke is aimed at a virtual (imaginary) target
Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon
Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO
Kinematic Theory - Sigma Lognormal Model (Plamondon et al. 2014)
Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon
Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO
Kinematic Theory - Sigma Lognormal Model (Plamondon et al. 2014)
Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon
Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO
Kinematic Theory - Sigma Lognormal Model (Plamondon et al. 2014)
Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon
Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO
Sigma Lognormal Model
STRUCTURE
“Virtual Targets”
KINEMATICS/HANDSTYLE
“Dynamic parameters”
Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon
Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO
User input
Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon
Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO
Reconstruction
(a) (b)
(c)
virtual targets
Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon
Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO
 Randomly perturb parameters of sigma lognormal model (e.g. +- 10%)
Data Augmentation
Video 1
Optimisation approach
Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie
Generating Calligraphic Trajectories with Model Predictive Control, 2017, Graphics Interface
Trajectory formation model Stylized trajectoriesStructure (motor plan)
Optimization / performance criterion
Computational Motor Control
• Complex hand and arm motions tend to be smooth
– Minimization of a cost or performance criterion.
– Minimum Square Derivative models (Flash & Hogan 1985, Flash 1983, Dingwell et al. 2004)
• Minimization of the squared magnitude of high derivatives of position
such as jerk (3rd, change in acceleration), snap (4th, change in jerk) etc…
• Optimal feedback control - Minimal intervention principle
(Todorov & Jordan 2002)
– Deviations from an average trajectory are only corrected if they interfere with
the required task precision.
– Higher variability → reduced effort → smoother trajectory
Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie
Generating Calligraphic Trajectories with Model Predictive Control, 2017, Graphics Interface
Cost function
Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie
Generating Calligraphic Trajectories with Model Predictive Control, 2017, Graphics Interface
Gaussian targets
Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie
Generating Calligraphic Trajectories with Model Predictive Control, 2017, Graphics Interface
Video 2
Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie
Generating Calligraphic Trajectories with Model Predictive Control, 2017, Graphics Interface
Procedural generation – random covariance
Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie
Dynamic Graffiti Stylisation with Stochastic Optimal Control, 2017, MOCO
Procedural generation – tied/semi-tied covariance
Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie
Dynamic Graffiti Stylisation with Stochastic Optimal Control, 2017, MOCO
Video 3
Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie
Dynamic Graffiti Stylisation with Stochastic Optimal Control, 2017, MOCO
Generative Glyphs
Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie
Dynamic Graffiti Stylisation with Stochastic Optimal Control, 2017, MOCO
Daniel Berio - Graffiti synthesis, a motion centric approach - Creative AI meetup
The end
Daniel Berio
d.berio@gold.ac.uk - http://www.enist.org
More info:
http://doc.gold.ac.uk/autograff
Relevant references:
Berio D., Akten M., Fol Leymarie F., Grierson M., Plamondon R.
Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks
Proc. of 4th Int’l Conf. on Movement Computing (MOCO). London, UK, 2017.
Berio D., Calinon S., Fol Leymarie F.
Dynamic Graffiti Stylisation with Stochastic Optimal Control
ACM Proceedings of the 4th International Conference on Movement and Computing. London, UK, June 2017.
Berio D., Calinon S., Fol Leymarie F.
Generating Calligraphic Trajectories with Model Predictive Control
Proceedings of Graphics Interface. Edmonton, Canada: Canadian Human-Computer Communications Society, May 2017.
1 of 33

Recommended

kinematic synthesis by
kinematic synthesiskinematic synthesis
kinematic synthesisvarun teja G.V.V
21.8K views13 slides
Hybridoma technology and production of monoclonal antibody by
Hybridoma technology and production of monoclonal antibodyHybridoma technology and production of monoclonal antibody
Hybridoma technology and production of monoclonal antibodyRajpal Choudhary
26.6K views15 slides
6.position analysis by
6.position analysis6.position analysis
6.position analysisvarun teja G.V.V
2.7K views36 slides
Linkage analysis and genome mapping by
Linkage analysis and genome mappingLinkage analysis and genome mapping
Linkage analysis and genome mappingRajpal Choudhary
9.3K views26 slides
Mechanism synthesis, graphical by
Mechanism synthesis, graphicalMechanism synthesis, graphical
Mechanism synthesis, graphicalMecanismos Ucr
12.5K views32 slides
Kinematic Synthesis by
Kinematic SynthesisKinematic Synthesis
Kinematic SynthesisYatin Singh
31.7K views62 slides

More Related Content

Similar to Daniel Berio - Graffiti synthesis, a motion centric approach - Creative AI meetup

Quantitative comparing design processes in digital and traditional sketching by
Quantitative comparing design processes in digital and traditional sketchingQuantitative comparing design processes in digital and traditional sketching
Quantitative comparing design processes in digital and traditional sketchingMohd Syahmi
477 views29 slides
Virtual/ Physical Co-Existing Design _Capturing Space Interactive Device by
Virtual/ Physical Co-Existing Design_Capturing Space Interactive Device   Virtual/ Physical Co-Existing Design_Capturing Space Interactive Device
Virtual/ Physical Co-Existing Design _Capturing Space Interactive Device Kai-Tzu Lu
187 views56 slides
Virtual/ Physical Co-Existing Design (CapX) by
Virtual/ Physical Co-Existing Design (CapX)Virtual/ Physical Co-Existing Design (CapX)
Virtual/ Physical Co-Existing Design (CapX)Kai-Tzu Lu
35 views56 slides
Cap xpresent by
Cap xpresentCap xpresent
Cap xpresentKai-Tzu Lu
353 views56 slides
Design in motion. The new frontier of interaction design by
Design in motion. The new frontier of interaction designDesign in motion. The new frontier of interaction design
Design in motion. The new frontier of interaction designAntonio De Pasquale
34.6K views79 slides
EWIC talk - 07 June, 2018 by
EWIC talk - 07 June, 2018EWIC talk - 07 June, 2018
EWIC talk - 07 June, 2018University of Huddersfield
96 views20 slides

Similar to Daniel Berio - Graffiti synthesis, a motion centric approach - Creative AI meetup(20)

Quantitative comparing design processes in digital and traditional sketching by Mohd Syahmi
Quantitative comparing design processes in digital and traditional sketchingQuantitative comparing design processes in digital and traditional sketching
Quantitative comparing design processes in digital and traditional sketching
Mohd Syahmi477 views
Virtual/ Physical Co-Existing Design _Capturing Space Interactive Device by Kai-Tzu Lu
Virtual/ Physical Co-Existing Design_Capturing Space Interactive Device   Virtual/ Physical Co-Existing Design_Capturing Space Interactive Device
Virtual/ Physical Co-Existing Design _Capturing Space Interactive Device
Kai-Tzu Lu187 views
Virtual/ Physical Co-Existing Design (CapX) by Kai-Tzu Lu
Virtual/ Physical Co-Existing Design (CapX)Virtual/ Physical Co-Existing Design (CapX)
Virtual/ Physical Co-Existing Design (CapX)
Kai-Tzu Lu35 views
Cap xpresent by Kai-Tzu Lu
Cap xpresentCap xpresent
Cap xpresent
Kai-Tzu Lu353 views
Design in motion. The new frontier of interaction design by Antonio De Pasquale
Design in motion. The new frontier of interaction designDesign in motion. The new frontier of interaction design
Design in motion. The new frontier of interaction design
Antonio De Pasquale34.6K views
Semantic_Visualisation_in_Design_Computing.pdf by Ely Hernandez
Semantic_Visualisation_in_Design_Computing.pdfSemantic_Visualisation_in_Design_Computing.pdf
Semantic_Visualisation_in_Design_Computing.pdf
Ely Hernandez68 views
Digital Dimensions by Emrecan Gulay by Emrecan Gulay
Digital Dimensions by Emrecan GulayDigital Dimensions by Emrecan Gulay
Digital Dimensions by Emrecan Gulay
Emrecan Gulay206 views
The Visual Data Discovery Tool by Lisa Brown
The Visual Data Discovery ToolThe Visual Data Discovery Tool
The Visual Data Discovery Tool
Lisa Brown2 views
보다 유연한 이미지 변환을 하려면? by 광희 이
보다 유연한 이미지 변환을 하려면?보다 유연한 이미지 변환을 하려면?
보다 유연한 이미지 변환을 하려면?
광희 이180 views
A Learned Representation for Artistic Style by Mayank Agarwal
A Learned Representation for Artistic StyleA Learned Representation for Artistic Style
A Learned Representation for Artistic Style
Mayank Agarwal90 views
Knowledge in (Geo)Visualisation by Chris Marmo
Knowledge in (Geo)VisualisationKnowledge in (Geo)Visualisation
Knowledge in (Geo)Visualisation
Chris Marmo562 views
Motion & Gesture Interactions in the digital age by Antonio De Pasquale
Motion & Gesture Interactions in the digital ageMotion & Gesture Interactions in the digital age
Motion & Gesture Interactions in the digital age
Antonio De Pasquale28.8K views
Codemotion2013depasquale by Vera Kovaleva
Codemotion2013depasqualeCodemotion2013depasquale
Codemotion2013depasquale
Vera Kovaleva893 views
ANIMATION PROJECT DOMAIN APPEAL IN MOTION CAPTURE ANIMATION (2015) by Sara Parker
ANIMATION PROJECT DOMAIN  APPEAL IN MOTION CAPTURE ANIMATION (2015)ANIMATION PROJECT DOMAIN  APPEAL IN MOTION CAPTURE ANIMATION (2015)
ANIMATION PROJECT DOMAIN APPEAL IN MOTION CAPTURE ANIMATION (2015)
Sara Parker2 views
Multimedia content based retrieval slideshare.ppt by govintech1
Multimedia content based retrieval slideshare.pptMultimedia content based retrieval slideshare.ppt
Multimedia content based retrieval slideshare.ppt
govintech16.6K views
Multi-modal embeddings: from discriminative to generative models and creative ai by Roelof Pieters
Multi-modal embeddings: from discriminative to generative models and creative aiMulti-modal embeddings: from discriminative to generative models and creative ai
Multi-modal embeddings: from discriminative to generative models and creative ai
Roelof Pieters2.3K views
PhD defense : Multi-points of view semantic enrichment of folksonomies by Freddy Limpens
PhD defense : Multi-points of view semantic enrichment of folksonomiesPhD defense : Multi-points of view semantic enrichment of folksonomies
PhD defense : Multi-points of view semantic enrichment of folksonomies
Freddy Limpens2.4K views

More from Luba Elliott

Luba Elliott - AI art - ICCV Conference by
Luba Elliott - AI art - ICCV ConferenceLuba Elliott - AI art - ICCV Conference
Luba Elliott - AI art - ICCV ConferenceLuba Elliott
435 views61 slides
Luba Elliott - AI in contemporary art practice - Oxford by
Luba Elliott - AI in contemporary art practice - OxfordLuba Elliott - AI in contemporary art practice - Oxford
Luba Elliott - AI in contemporary art practice - OxfordLuba Elliott
295 views81 slides
Luba Elliott - AI in recent art practice - ML Prague by
Luba Elliott - AI in recent art practice - ML PragueLuba Elliott - AI in recent art practice - ML Prague
Luba Elliott - AI in recent art practice - ML PragueLuba Elliott
202 views38 slides
Three Images of the New - Richard Hames - Creative AI meetup by
Three Images of the New - Richard Hames - Creative AI meetupThree Images of the New - Richard Hames - Creative AI meetup
Three Images of the New - Richard Hames - Creative AI meetupLuba Elliott
136 views21 slides
AI Art Gallery Overview - Luba Elliott - NeurIPS Creativity Workshop by
AI Art Gallery Overview - Luba Elliott - NeurIPS Creativity WorkshopAI Art Gallery Overview - Luba Elliott - NeurIPS Creativity Workshop
AI Art Gallery Overview - Luba Elliott - NeurIPS Creativity WorkshopLuba Elliott
156 views25 slides
Creativity is Intelligence - Kenneth Stanley - NeurIPS Creativity Workshop by
Creativity is Intelligence - Kenneth Stanley - NeurIPS Creativity WorkshopCreativity is Intelligence - Kenneth Stanley - NeurIPS Creativity Workshop
Creativity is Intelligence - Kenneth Stanley - NeurIPS Creativity WorkshopLuba Elliott
268 views37 slides

More from Luba Elliott(20)

Luba Elliott - AI art - ICCV Conference by Luba Elliott
Luba Elliott - AI art - ICCV ConferenceLuba Elliott - AI art - ICCV Conference
Luba Elliott - AI art - ICCV Conference
Luba Elliott435 views
Luba Elliott - AI in contemporary art practice - Oxford by Luba Elliott
Luba Elliott - AI in contemporary art practice - OxfordLuba Elliott - AI in contemporary art practice - Oxford
Luba Elliott - AI in contemporary art practice - Oxford
Luba Elliott295 views
Luba Elliott - AI in recent art practice - ML Prague by Luba Elliott
Luba Elliott - AI in recent art practice - ML PragueLuba Elliott - AI in recent art practice - ML Prague
Luba Elliott - AI in recent art practice - ML Prague
Luba Elliott202 views
Three Images of the New - Richard Hames - Creative AI meetup by Luba Elliott
Three Images of the New - Richard Hames - Creative AI meetupThree Images of the New - Richard Hames - Creative AI meetup
Three Images of the New - Richard Hames - Creative AI meetup
Luba Elliott136 views
AI Art Gallery Overview - Luba Elliott - NeurIPS Creativity Workshop by Luba Elliott
AI Art Gallery Overview - Luba Elliott - NeurIPS Creativity WorkshopAI Art Gallery Overview - Luba Elliott - NeurIPS Creativity Workshop
AI Art Gallery Overview - Luba Elliott - NeurIPS Creativity Workshop
Luba Elliott156 views
Creativity is Intelligence - Kenneth Stanley - NeurIPS Creativity Workshop by Luba Elliott
Creativity is Intelligence - Kenneth Stanley - NeurIPS Creativity WorkshopCreativity is Intelligence - Kenneth Stanley - NeurIPS Creativity Workshop
Creativity is Intelligence - Kenneth Stanley - NeurIPS Creativity Workshop
Luba Elliott268 views
Seen by machine: Computational Spectatorship in the BBC Archive by Luba Elliott
Seen by machine: Computational Spectatorship in the BBC ArchiveSeen by machine: Computational Spectatorship in the BBC Archive
Seen by machine: Computational Spectatorship in the BBC Archive
Luba Elliott94 views
Luba Elliott AI art overview by Luba Elliott
Luba Elliott AI art overview Luba Elliott AI art overview
Luba Elliott AI art overview
Luba Elliott206 views
Natasha Jaques - Learning via Social Awareness - Creative AI meetup by Luba Elliott
Natasha Jaques - Learning via Social Awareness - Creative AI meetupNatasha Jaques - Learning via Social Awareness - Creative AI meetup
Natasha Jaques - Learning via Social Awareness - Creative AI meetup
Luba Elliott635 views
Sander Dieleman - Generating music in the raw audio domain - Creative AI meetup by Luba Elliott
Sander Dieleman - Generating music in the raw audio domain - Creative AI meetupSander Dieleman - Generating music in the raw audio domain - Creative AI meetup
Sander Dieleman - Generating music in the raw audio domain - Creative AI meetup
Luba Elliott298 views
Marco Marchesi - Practical uses of style transfer in the creative industry by Luba Elliott
Marco Marchesi - Practical uses of style transfer in the creative industryMarco Marchesi - Practical uses of style transfer in the creative industry
Marco Marchesi - Practical uses of style transfer in the creative industry
Luba Elliott946 views
Hooman Shayani - CAD/CAM in the Age of AI: Designers’ Journey from Earth to Sky by Luba Elliott
Hooman Shayani - CAD/CAM in the Age of AI: Designers’ Journey from Earth to SkyHooman Shayani - CAD/CAM in the Age of AI: Designers’ Journey from Earth to Sky
Hooman Shayani - CAD/CAM in the Age of AI: Designers’ Journey from Earth to Sky
Luba Elliott583 views
Lucas Theis - Compressing Images with Neural Networks - Creative AI meetup by Luba Elliott
Lucas Theis - Compressing Images with Neural Networks - Creative AI meetupLucas Theis - Compressing Images with Neural Networks - Creative AI meetup
Lucas Theis - Compressing Images with Neural Networks - Creative AI meetup
Luba Elliott467 views
Emily Denton - Unsupervised Learning of Disentangled Representations from Vid... by Luba Elliott
Emily Denton - Unsupervised Learning of Disentangled Representations from Vid...Emily Denton - Unsupervised Learning of Disentangled Representations from Vid...
Emily Denton - Unsupervised Learning of Disentangled Representations from Vid...
Luba Elliott1K views
Luba Elliott - Seeing AI through Art by Luba Elliott
Luba Elliott - Seeing AI through ArtLuba Elliott - Seeing AI through Art
Luba Elliott - Seeing AI through Art
Luba Elliott293 views
Georgia Ward Dyer - O Time thy pyramids - Creative AI meetup by Luba Elliott
Georgia Ward Dyer - O Time thy pyramids - Creative AI meetupGeorgia Ward Dyer - O Time thy pyramids - Creative AI meetup
Georgia Ward Dyer - O Time thy pyramids - Creative AI meetup
Luba Elliott425 views
Ali Eslami - Artificial Intelligence and Computer Aided Design - Creative AI ... by Luba Elliott
Ali Eslami - Artificial Intelligence and Computer Aided Design - Creative AI ...Ali Eslami - Artificial Intelligence and Computer Aided Design - Creative AI ...
Ali Eslami - Artificial Intelligence and Computer Aided Design - Creative AI ...
Luba Elliott944 views
Daghan Cam - Adaptive Autonomous Manufacturing with AI - Creative AI meetup by Luba Elliott
Daghan Cam - Adaptive Autonomous Manufacturing with AI - Creative AI meetupDaghan Cam - Adaptive Autonomous Manufacturing with AI - Creative AI meetup
Daghan Cam - Adaptive Autonomous Manufacturing with AI - Creative AI meetup
Luba Elliott471 views
Martin Arjovsky - Wasserstein GAN - Creative AI meetup by Luba Elliott
Martin Arjovsky - Wasserstein GAN - Creative AI meetupMartin Arjovsky - Wasserstein GAN - Creative AI meetup
Martin Arjovsky - Wasserstein GAN - Creative AI meetup
Luba Elliott539 views

Recently uploaded

iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas... by
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...Bernd Ruecker
50 views69 slides
Confidence in CloudStack - Aron Wagner, Nathan Gleason - Americ by
Confidence in CloudStack - Aron Wagner, Nathan Gleason - AmericConfidence in CloudStack - Aron Wagner, Nathan Gleason - Americ
Confidence in CloudStack - Aron Wagner, Nathan Gleason - AmericShapeBlue
58 views9 slides
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R... by
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...ShapeBlue
105 views15 slides
KVM Security Groups Under the Hood - Wido den Hollander - Your.Online by
KVM Security Groups Under the Hood - Wido den Hollander - Your.OnlineKVM Security Groups Under the Hood - Wido den Hollander - Your.Online
KVM Security Groups Under the Hood - Wido den Hollander - Your.OnlineShapeBlue
154 views19 slides
"Surviving highload with Node.js", Andrii Shumada by
"Surviving highload with Node.js", Andrii Shumada "Surviving highload with Node.js", Andrii Shumada
"Surviving highload with Node.js", Andrii Shumada Fwdays
49 views29 slides
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P... by
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...ShapeBlue
120 views62 slides

Recently uploaded(20)

iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas... by Bernd Ruecker
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...
Bernd Ruecker50 views
Confidence in CloudStack - Aron Wagner, Nathan Gleason - Americ by ShapeBlue
Confidence in CloudStack - Aron Wagner, Nathan Gleason - AmericConfidence in CloudStack - Aron Wagner, Nathan Gleason - Americ
Confidence in CloudStack - Aron Wagner, Nathan Gleason - Americ
ShapeBlue58 views
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R... by ShapeBlue
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...
ShapeBlue105 views
KVM Security Groups Under the Hood - Wido den Hollander - Your.Online by ShapeBlue
KVM Security Groups Under the Hood - Wido den Hollander - Your.OnlineKVM Security Groups Under the Hood - Wido den Hollander - Your.Online
KVM Security Groups Under the Hood - Wido den Hollander - Your.Online
ShapeBlue154 views
"Surviving highload with Node.js", Andrii Shumada by Fwdays
"Surviving highload with Node.js", Andrii Shumada "Surviving highload with Node.js", Andrii Shumada
"Surviving highload with Node.js", Andrii Shumada
Fwdays49 views
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P... by ShapeBlue
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...
ShapeBlue120 views
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f... by TrustArc
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...
TrustArc130 views
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLive by Network Automation Forum
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLiveAutomating a World-Class Technology Conference; Behind the Scenes of CiscoLive
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLive
Extending KVM Host HA for Non-NFS Storage - Alex Ivanov - StorPool by ShapeBlue
Extending KVM Host HA for Non-NFS Storage -  Alex Ivanov - StorPoolExtending KVM Host HA for Non-NFS Storage -  Alex Ivanov - StorPool
Extending KVM Host HA for Non-NFS Storage - Alex Ivanov - StorPool
ShapeBlue56 views
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue by ShapeBlue
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlueMigrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue
ShapeBlue147 views
Zero to Cloud Hero: Crafting a Private Cloud from Scratch with XCP-ng, Xen Or... by ShapeBlue
Zero to Cloud Hero: Crafting a Private Cloud from Scratch with XCP-ng, Xen Or...Zero to Cloud Hero: Crafting a Private Cloud from Scratch with XCP-ng, Xen Or...
Zero to Cloud Hero: Crafting a Private Cloud from Scratch with XCP-ng, Xen Or...
ShapeBlue128 views
Keynote Talk: Open Source is Not Dead - Charles Schulz - Vates by ShapeBlue
Keynote Talk: Open Source is Not Dead - Charles Schulz - VatesKeynote Talk: Open Source is Not Dead - Charles Schulz - Vates
Keynote Talk: Open Source is Not Dead - Charles Schulz - Vates
ShapeBlue178 views
Import Export Virtual Machine for KVM Hypervisor - Ayush Pandey - University ... by ShapeBlue
Import Export Virtual Machine for KVM Hypervisor - Ayush Pandey - University ...Import Export Virtual Machine for KVM Hypervisor - Ayush Pandey - University ...
Import Export Virtual Machine for KVM Hypervisor - Ayush Pandey - University ...
ShapeBlue48 views
Digital Personal Data Protection (DPDP) Practical Approach For CISOs by Priyanka Aash
Digital Personal Data Protection (DPDP) Practical Approach For CISOsDigital Personal Data Protection (DPDP) Practical Approach For CISOs
Digital Personal Data Protection (DPDP) Practical Approach For CISOs
Priyanka Aash103 views
What’s New in CloudStack 4.19 - Abhishek Kumar - ShapeBlue by ShapeBlue
What’s New in CloudStack 4.19 - Abhishek Kumar - ShapeBlueWhat’s New in CloudStack 4.19 - Abhishek Kumar - ShapeBlue
What’s New in CloudStack 4.19 - Abhishek Kumar - ShapeBlue
ShapeBlue191 views
How to Re-use Old Hardware with CloudStack. Saving Money and the Environment ... by ShapeBlue
How to Re-use Old Hardware with CloudStack. Saving Money and the Environment ...How to Re-use Old Hardware with CloudStack. Saving Money and the Environment ...
How to Re-use Old Hardware with CloudStack. Saving Money and the Environment ...
ShapeBlue97 views
Backroll, News and Demo - Pierre Charton, Matthias Dhellin, Ousmane Diarra - ... by ShapeBlue
Backroll, News and Demo - Pierre Charton, Matthias Dhellin, Ousmane Diarra - ...Backroll, News and Demo - Pierre Charton, Matthias Dhellin, Ousmane Diarra - ...
Backroll, News and Demo - Pierre Charton, Matthias Dhellin, Ousmane Diarra - ...
ShapeBlue121 views
DRBD Deep Dive - Philipp Reisner - LINBIT by ShapeBlue
DRBD Deep Dive - Philipp Reisner - LINBITDRBD Deep Dive - Philipp Reisner - LINBIT
DRBD Deep Dive - Philipp Reisner - LINBIT
ShapeBlue110 views
Declarative Kubernetes Cluster Deployment with Cloudstack and Cluster API - O... by ShapeBlue
Declarative Kubernetes Cluster Deployment with Cloudstack and Cluster API - O...Declarative Kubernetes Cluster Deployment with Cloudstack and Cluster API - O...
Declarative Kubernetes Cluster Deployment with Cloudstack and Cluster API - O...
ShapeBlue59 views

Daniel Berio - Graffiti synthesis, a motion centric approach - Creative AI meetup

  • 1. Autograff Optimality Principles in the Procedural Generation of Graffiti Style Graffiti synthesis, a motion centric approach Daniel Berio http://doc.gold.ac.uk/autograf @colormotor
  • 5. Graffiti art - tags • Elementary “Atom” of graffiti art • Highly stylized signature denoting an artist’s pseudonym • Generated by rapidly executed and well learned movements – Different style are referred to as “hand styles” – In graffiti jargon, a well made tag has ”flow”
  • 6. Embodied perception • Well known relations between kinematics and geometry of human movements (e.g. power laws) (Lacquaniti et al. 1983) • Observation of a human made trace triggers the mental recovery of the movement underlying its production (Freedberg and Gallese 2007, Longcamp et al. 2006, Pignocchi 2010) • Such recovery influences aesthetic appreciation (Leder et al. 2012)
  • 7. Embodied perception • Well known relations between kinematics and geometry of human movements (e.g. power laws) (Lacquaniti et al. 1983) • Observation of a human made trace triggers the mental recovery of the movement underlying its production (Freedberg and Gallese 2007, Longcamp et al. 2006, Pignocchi 2010) • Such recovery influences aesthetic appreciation (Leder et al. 2012) • It follows that an appropriate simulation of movement may trigger a similar effect in the viewer for computer generated traces.
  • 8. Graffiti Taxonomy Evan Roth, Graffiti Taxonomy https://www.moma.org/collection/works/147174
  • 11. Movement centric curve generation Trajectory formation model Stylized trajectoriesControl polygon / motor plan Parameters ?
  • 12. Data driven approach Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO Trajectory formation model Stylized trajectoriesStructure (motor plan)
  • 13. Graphonomics The scientific field ”concerned with the systematic relationships involved in the generation and analysis of the handwriting and drawing movements, and the resulting traces of writing and drawing instruments” (Kao, Hoosain, & Van Galen, 1986) Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO
  • 14. Graphonomics - principles • Aiming movements assume a “bell shaped” speed profile (Morasso, 1981) • Handwriting movements can be decomposed into a discrete number of aiming movement primitives (strokes) (Teulings and Schomaker 1993, Mussa Ivaldi and Solla 2004, Sosnik et al. 2004, Plamondon et al. 2014) – Also characterized by the same bell shaped speed profile. – Each stroke is aimed at a virtual (imaginary) target Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO
  • 15. Kinematic Theory - Sigma Lognormal Model (Plamondon et al. 2014) Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO
  • 16. Kinematic Theory - Sigma Lognormal Model (Plamondon et al. 2014) Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO
  • 17. Kinematic Theory - Sigma Lognormal Model (Plamondon et al. 2014) Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO
  • 18. Sigma Lognormal Model STRUCTURE “Virtual Targets” KINEMATICS/HANDSTYLE “Dynamic parameters” Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO
  • 19. User input Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO
  • 20. Reconstruction (a) (b) (c) virtual targets Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks, 2017, MOCO
  • 21.  Randomly perturb parameters of sigma lognormal model (e.g. +- 10%) Data Augmentation
  • 23. Optimisation approach Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie Generating Calligraphic Trajectories with Model Predictive Control, 2017, Graphics Interface Trajectory formation model Stylized trajectoriesStructure (motor plan) Optimization / performance criterion
  • 24. Computational Motor Control • Complex hand and arm motions tend to be smooth – Minimization of a cost or performance criterion. – Minimum Square Derivative models (Flash & Hogan 1985, Flash 1983, Dingwell et al. 2004) • Minimization of the squared magnitude of high derivatives of position such as jerk (3rd, change in acceleration), snap (4th, change in jerk) etc… • Optimal feedback control - Minimal intervention principle (Todorov & Jordan 2002) – Deviations from an average trajectory are only corrected if they interfere with the required task precision. – Higher variability → reduced effort → smoother trajectory Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie Generating Calligraphic Trajectories with Model Predictive Control, 2017, Graphics Interface
  • 25. Cost function Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie Generating Calligraphic Trajectories with Model Predictive Control, 2017, Graphics Interface
  • 26. Gaussian targets Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie Generating Calligraphic Trajectories with Model Predictive Control, 2017, Graphics Interface
  • 27. Video 2 Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie Generating Calligraphic Trajectories with Model Predictive Control, 2017, Graphics Interface
  • 28. Procedural generation – random covariance Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie Dynamic Graffiti Stylisation with Stochastic Optimal Control, 2017, MOCO
  • 29. Procedural generation – tied/semi-tied covariance Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie Dynamic Graffiti Stylisation with Stochastic Optimal Control, 2017, MOCO
  • 30. Video 3 Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie Dynamic Graffiti Stylisation with Stochastic Optimal Control, 2017, MOCO
  • 31. Generative Glyphs Daniel Berio, Sylvain Calinon, Frederic Fol Leymarie Dynamic Graffiti Stylisation with Stochastic Optimal Control, 2017, MOCO
  • 33. The end Daniel Berio d.berio@gold.ac.uk - http://www.enist.org More info: http://doc.gold.ac.uk/autograff Relevant references: Berio D., Akten M., Fol Leymarie F., Grierson M., Plamondon R. Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks Proc. of 4th Int’l Conf. on Movement Computing (MOCO). London, UK, 2017. Berio D., Calinon S., Fol Leymarie F. Dynamic Graffiti Stylisation with Stochastic Optimal Control ACM Proceedings of the 4th International Conference on Movement and Computing. London, UK, June 2017. Berio D., Calinon S., Fol Leymarie F. Generating Calligraphic Trajectories with Model Predictive Control Proceedings of Graphics Interface. Edmonton, Canada: Canadian Human-Computer Communications Society, May 2017.