SlideShare a Scribd company logo
Leveraging machine intelligence
to improve sensory experiences
Dr Esin Yavuz, Co-founder & Chief Scientist
MI Garage Meetup: “How can the creative industries use AI?”
7 November 2018
Augmenting sensory perception
with machine intelligence
Linking machine intelligence and human perception requires
real-time and automated image processing. To enable this, we
are building a platform that allows fast and automated
processing of images using AI.
Outline
●
Background & State of the art
●
AI for photorealistic image transformations
●
Automating image editing
What is AI?
●
“Science of making machines do things that would require intelligence if done by men.”
Minsky
●
Often used to refer to statistical methods that aim to fnd structure and regularities in data
●
Used for making deductions based on observations
●
Applied to problem solving, reasoning, natural language processing, machine perception
●
2006: NVIDIA releases CUDA for general purpose GPU
computing
High-performance computing becomes easier to use
●
2010: ImageNet Large Scale Visual Recognition challenge
-Classifcation task based on a dataset of 10M images in
10K+ classes
Importance of number of examples and problem defnition
●
2012: Alexnet achieves top-5 error of 15.3%, more than 10.8
percentage points lower than that of the runner up on
ImageNet competition using a deep convolutional network
Beginning of the Deep Learning era
Breakthroughs in the last decade
https://distill.pub/2017/feature-visualization/
Deep Dream (Google) 2015
●
Initially designed as a tool to understand internal properties of neural networks
●
Whatever the network sees, it adjust the other pixels to see more of it
●
Allows creative image manipulations based on internal structure of a neural network
Neural Style Transfer – Gatys et al. 2016
Combining the
content of an image
with the style of
another image
https://deepart.io/
https://prisma-ai.com/
Image generation with Generative Adversarial Nets
(GAN) – Goodfellow et al. 2014
More recent GAN examples
Brock et al - BigGAN (Deepmind) 2018Karras et al. (NVIDIA) 2017
Evolving to be a new tool for artistic creation
Style Transfer with CycleGAN
Artistic style transfer with GAN-based methods
Drawbacks
●
While artistic style transfer can
be easily achieved, photorealistic
transformations are not easy
●
Mostly support low-res, if not
they need massive computational
power
●
Diffcult to generalise to different
content domains
Limitations of CycleGAN
Why do we need photorealistic transformations?
●
Good quality visual content is indispensable for a better
communication through visuals. However, creating good quality
visuals needs expertise and it is time consuming.
●
Existing tools for image flters provide synthetic results that look
similar, most are slow, do not scale for bulk image processing, and
still require substantial user expertise.
●
Apart from content creation, there is a need in other felds such as
data augmentation, video game development, rendering, enhancing
video streams.
Problems of applying AI to casual photography
Flickr/Mr Boss
Flickr/Yuma Hori
Flickr/Bex Walton
AI filers lhal work witlh any l pe of itmages
Transform any type of image
to refect different daytime
lighting conditions
AI-powered itmage filers
AI-powered itmage filers
AI-powered itmage filers
More examples here: cyanapse.com/ai-tech/photorealistic-image-flters
●
Use AI-powered photorealistic flters
that work with any type of photos
●
Automate dull image editing tasks
●
Enable bulk image editing with
custom pipelines
Automated Image Editing Platform
1- Back-end API for fast and automated image processing
2- Front-end App for user-friendly interface
●
RESTful API with intuitive
endpoints
●
Bulk processing that scales
to users’ needs
●
User-defned image editing
pipelines
●
Includes AI-enhanced
image styling flters
Automating image editing
Front-end
●
Mobile and web app to try out
AI flters
●
Use AI photo flters in just a
few clicks
●
Instantaneous generation of
various previews
●
Less than a second to
enhance 4k-res images, 40
ms for a low-res image
Advantages
●
4k resolution images are enhanced in less than a second
●
AI transformations run in the cloud (fexible and scalable)
●
We provide image enhancements that are photorealistic and that work for
every type of photos
●
Minimise the time spent on creating good quality content, allowing content
creators to focus on more important tasks
●
Enable real-time and photorealistic enhancements of video streams with
minimal human intervention
●
Generate multiple possible transformations to help content creators
preview the results beforehand, and to pass their messages better
Thank you!
Email: info@cyanapse.com
Register here:
cyanapse.com/beta-testing
@cyanapse

More Related Content

Similar to Cyanapse talk photorealisticf_ilters_migaragemeetup_7nov2018

IEEE - Consumer Electronics Trends Opportunities (2015)
IEEE - Consumer Electronics Trends Opportunities (2015)IEEE - Consumer Electronics Trends Opportunities (2015)
IEEE - Consumer Electronics Trends Opportunities (2015)
Prabindh Sundareson
 
[DSC Europe 22] Developing Visual AI Solutions for Online Marketplaces - Mlad...
[DSC Europe 22] Developing Visual AI Solutions for Online Marketplaces - Mlad...[DSC Europe 22] Developing Visual AI Solutions for Online Marketplaces - Mlad...
[DSC Europe 22] Developing Visual AI Solutions for Online Marketplaces - Mlad...
DataScienceConferenc1
 
06108870 analytical study of parallel and distributed image processing 2011
06108870 analytical study of parallel and distributed image processing 201106108870 analytical study of parallel and distributed image processing 2011
06108870 analytical study of parallel and distributed image processing 2011
Kiran Verma
 
Sf big analytics: bighead
Sf big analytics: bigheadSf big analytics: bighead
Sf big analytics: bighead
Chester Chen
 
CloudMile Product & Service (EN)
CloudMile Product & Service (EN)CloudMile Product & Service (EN)
CloudMile Product & Service (EN)
Karen (Mu Hsuan) Chen
 
Keynote: Faster, Better, Cheaper: Pick all Three! By Miles Ward of Google
Keynote: Faster, Better, Cheaper: Pick all Three! By Miles Ward of GoogleKeynote: Faster, Better, Cheaper: Pick all Three! By Miles Ward of Google
Keynote: Faster, Better, Cheaper: Pick all Three! By Miles Ward of Google
ETCenter
 
FACE COUNTING USING OPEN CV & PYTHON FOR ANALYZING UNUSUAL EVENTS IN CROWDS
FACE COUNTING USING OPEN CV & PYTHON FOR ANALYZING UNUSUAL EVENTS IN CROWDSFACE COUNTING USING OPEN CV & PYTHON FOR ANALYZING UNUSUAL EVENTS IN CROWDS
FACE COUNTING USING OPEN CV & PYTHON FOR ANALYZING UNUSUAL EVENTS IN CROWDS
IRJET Journal
 
Stateful Performance Measurement with PageSpeed API & Munin
Stateful Performance Measurement with PageSpeed API & MuninStateful Performance Measurement with PageSpeed API & Munin
Stateful Performance Measurement with PageSpeed API & MuninMichael Kröll
 
Challenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate ImagingChallenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Adhesh Shrivastava
 
DN18 | Demystifying the Buzz in Machine Learning! (This Time for Real) | Dat ...
DN18 | Demystifying the Buzz in Machine Learning! (This Time for Real) | Dat ...DN18 | Demystifying the Buzz in Machine Learning! (This Time for Real) | Dat ...
DN18 | Demystifying the Buzz in Machine Learning! (This Time for Real) | Dat ...
Dataconomy Media
 
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Codemotion
 
An Analysis on the Use of Image Design with Generative AI Technologies
An Analysis on the Use of Image Design with Generative AI TechnologiesAn Analysis on the Use of Image Design with Generative AI Technologies
An Analysis on the Use of Image Design with Generative AI Technologies
ijtsrd
 
Photo Editing And Sharing Web Application With AI- Assisted Features
Photo Editing And Sharing Web Application With AI- Assisted FeaturesPhoto Editing And Sharing Web Application With AI- Assisted Features
Photo Editing And Sharing Web Application With AI- Assisted Features
IRJET Journal
 
Mohamed Amrith Project and Contributions
Mohamed Amrith Project and ContributionsMohamed Amrith Project and Contributions
Mohamed Amrith Project and Contributions
MuslimVoice3
 
Better images for video - Jeremy Brown
Better images for video - Jeremy BrownBetter images for video - Jeremy Brown
Better images for video - Jeremy Brown
Jeremy Brown
 
46.-Applications-of-AI-Image-Processing.pdf
46.-Applications-of-AI-Image-Processing.pdf46.-Applications-of-AI-Image-Processing.pdf
46.-Applications-of-AI-Image-Processing.pdf
monikag2613
 
How ABB shapes the future of industry with Microsoft HoloLens and Unity - Uni...
How ABB shapes the future of industry with Microsoft HoloLens and Unity - Uni...How ABB shapes the future of industry with Microsoft HoloLens and Unity - Uni...
How ABB shapes the future of industry with Microsoft HoloLens and Unity - Uni...
Unity Technologies
 
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNINGHANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
IRJET Journal
 
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNINGHANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
IRJET Journal
 
Sidiq Permana - Building For The Next Billion Users
Sidiq Permana - Building For The Next Billion UsersSidiq Permana - Building For The Next Billion Users
Sidiq Permana - Building For The Next Billion Users
Dicoding
 

Similar to Cyanapse talk photorealisticf_ilters_migaragemeetup_7nov2018 (20)

IEEE - Consumer Electronics Trends Opportunities (2015)
IEEE - Consumer Electronics Trends Opportunities (2015)IEEE - Consumer Electronics Trends Opportunities (2015)
IEEE - Consumer Electronics Trends Opportunities (2015)
 
[DSC Europe 22] Developing Visual AI Solutions for Online Marketplaces - Mlad...
[DSC Europe 22] Developing Visual AI Solutions for Online Marketplaces - Mlad...[DSC Europe 22] Developing Visual AI Solutions for Online Marketplaces - Mlad...
[DSC Europe 22] Developing Visual AI Solutions for Online Marketplaces - Mlad...
 
06108870 analytical study of parallel and distributed image processing 2011
06108870 analytical study of parallel and distributed image processing 201106108870 analytical study of parallel and distributed image processing 2011
06108870 analytical study of parallel and distributed image processing 2011
 
Sf big analytics: bighead
Sf big analytics: bigheadSf big analytics: bighead
Sf big analytics: bighead
 
CloudMile Product & Service (EN)
CloudMile Product & Service (EN)CloudMile Product & Service (EN)
CloudMile Product & Service (EN)
 
Keynote: Faster, Better, Cheaper: Pick all Three! By Miles Ward of Google
Keynote: Faster, Better, Cheaper: Pick all Three! By Miles Ward of GoogleKeynote: Faster, Better, Cheaper: Pick all Three! By Miles Ward of Google
Keynote: Faster, Better, Cheaper: Pick all Three! By Miles Ward of Google
 
FACE COUNTING USING OPEN CV & PYTHON FOR ANALYZING UNUSUAL EVENTS IN CROWDS
FACE COUNTING USING OPEN CV & PYTHON FOR ANALYZING UNUSUAL EVENTS IN CROWDSFACE COUNTING USING OPEN CV & PYTHON FOR ANALYZING UNUSUAL EVENTS IN CROWDS
FACE COUNTING USING OPEN CV & PYTHON FOR ANALYZING UNUSUAL EVENTS IN CROWDS
 
Stateful Performance Measurement with PageSpeed API & Munin
Stateful Performance Measurement with PageSpeed API & MuninStateful Performance Measurement with PageSpeed API & Munin
Stateful Performance Measurement with PageSpeed API & Munin
 
Challenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate ImagingChallenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
 
DN18 | Demystifying the Buzz in Machine Learning! (This Time for Real) | Dat ...
DN18 | Demystifying the Buzz in Machine Learning! (This Time for Real) | Dat ...DN18 | Demystifying the Buzz in Machine Learning! (This Time for Real) | Dat ...
DN18 | Demystifying the Buzz in Machine Learning! (This Time for Real) | Dat ...
 
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
 
An Analysis on the Use of Image Design with Generative AI Technologies
An Analysis on the Use of Image Design with Generative AI TechnologiesAn Analysis on the Use of Image Design with Generative AI Technologies
An Analysis on the Use of Image Design with Generative AI Technologies
 
Photo Editing And Sharing Web Application With AI- Assisted Features
Photo Editing And Sharing Web Application With AI- Assisted FeaturesPhoto Editing And Sharing Web Application With AI- Assisted Features
Photo Editing And Sharing Web Application With AI- Assisted Features
 
Mohamed Amrith Project and Contributions
Mohamed Amrith Project and ContributionsMohamed Amrith Project and Contributions
Mohamed Amrith Project and Contributions
 
Better images for video - Jeremy Brown
Better images for video - Jeremy BrownBetter images for video - Jeremy Brown
Better images for video - Jeremy Brown
 
46.-Applications-of-AI-Image-Processing.pdf
46.-Applications-of-AI-Image-Processing.pdf46.-Applications-of-AI-Image-Processing.pdf
46.-Applications-of-AI-Image-Processing.pdf
 
How ABB shapes the future of industry with Microsoft HoloLens and Unity - Uni...
How ABB shapes the future of industry with Microsoft HoloLens and Unity - Uni...How ABB shapes the future of industry with Microsoft HoloLens and Unity - Uni...
How ABB shapes the future of industry with Microsoft HoloLens and Unity - Uni...
 
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNINGHANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
 
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNINGHANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
 
Sidiq Permana - Building For The Next Billion Users
Sidiq Permana - Building For The Next Billion UsersSidiq Permana - Building For The Next Billion Users
Sidiq Permana - Building For The Next Billion Users
 

More from Peter Bloomfield

Ai for urban traffic control neil walton_2020
Ai for urban traffic control neil walton_2020Ai for urban traffic control neil walton_2020
Ai for urban traffic control neil walton_2020
Peter Bloomfield
 
Geospatial intelligence satellite applications catapult pdf - july 23 2019
Geospatial intelligence   satellite applications catapult pdf - july 23 2019Geospatial intelligence   satellite applications catapult pdf - july 23 2019
Geospatial intelligence satellite applications catapult pdf - july 23 2019
Peter Bloomfield
 
Prem Gill Seals From Space
Prem Gill Seals From SpacePrem Gill Seals From Space
Prem Gill Seals From Space
Peter Bloomfield
 
David Petit Deimos presentation EO
David Petit Deimos presentation EODavid Petit Deimos presentation EO
David Petit Deimos presentation EO
Peter Bloomfield
 
Cray mi garage av event march 28 2019 pdf
Cray mi garage av event march 28 2019 pdfCray mi garage av event march 28 2019 pdf
Cray mi garage av event march 28 2019 pdf
Peter Bloomfield
 
5 g vehicular_comms_katsaros
5 g vehicular_comms_katsaros5 g vehicular_comms_katsaros
5 g vehicular_comms_katsaros
Peter Bloomfield
 
Tsc cav@digital catapult_march2019
Tsc cav@digital catapult_march2019Tsc cav@digital catapult_march2019
Tsc cav@digital catapult_march2019
Peter Bloomfield
 
Yossarian 2018 intro
Yossarian 2018 introYossarian 2018 intro
Yossarian 2018 intro
Peter Bloomfield
 
Armin mustafa talk_08.11.18_a_imeetup
Armin mustafa talk_08.11.18_a_imeetupArmin mustafa talk_08.11.18_a_imeetup
Armin mustafa talk_08.11.18_a_imeetup
Peter Bloomfield
 
Caspian machine learning garage
Caspian machine learning garageCaspian machine learning garage
Caspian machine learning garage
Peter Bloomfield
 
Pablo Suau - DWP Digital
Pablo Suau - DWP DigitalPablo Suau - DWP Digital
Pablo Suau - DWP Digital
Peter Bloomfield
 

More from Peter Bloomfield (11)

Ai for urban traffic control neil walton_2020
Ai for urban traffic control neil walton_2020Ai for urban traffic control neil walton_2020
Ai for urban traffic control neil walton_2020
 
Geospatial intelligence satellite applications catapult pdf - july 23 2019
Geospatial intelligence   satellite applications catapult pdf - july 23 2019Geospatial intelligence   satellite applications catapult pdf - july 23 2019
Geospatial intelligence satellite applications catapult pdf - july 23 2019
 
Prem Gill Seals From Space
Prem Gill Seals From SpacePrem Gill Seals From Space
Prem Gill Seals From Space
 
David Petit Deimos presentation EO
David Petit Deimos presentation EODavid Petit Deimos presentation EO
David Petit Deimos presentation EO
 
Cray mi garage av event march 28 2019 pdf
Cray mi garage av event march 28 2019 pdfCray mi garage av event march 28 2019 pdf
Cray mi garage av event march 28 2019 pdf
 
5 g vehicular_comms_katsaros
5 g vehicular_comms_katsaros5 g vehicular_comms_katsaros
5 g vehicular_comms_katsaros
 
Tsc cav@digital catapult_march2019
Tsc cav@digital catapult_march2019Tsc cav@digital catapult_march2019
Tsc cav@digital catapult_march2019
 
Yossarian 2018 intro
Yossarian 2018 introYossarian 2018 intro
Yossarian 2018 intro
 
Armin mustafa talk_08.11.18_a_imeetup
Armin mustafa talk_08.11.18_a_imeetupArmin mustafa talk_08.11.18_a_imeetup
Armin mustafa talk_08.11.18_a_imeetup
 
Caspian machine learning garage
Caspian machine learning garageCaspian machine learning garage
Caspian machine learning garage
 
Pablo Suau - DWP Digital
Pablo Suau - DWP DigitalPablo Suau - DWP Digital
Pablo Suau - DWP Digital
 

Recently uploaded

Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
g2nightmarescribd
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
Safe Software
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance
 
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
Sri Ambati
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
Alan Dix
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
KatiaHIMEUR1
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
RTTS
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Tobias Schneck
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
Elena Simperl
 
Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........
Alison B. Lowndes
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
Prayukth K V
 
Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*
Frank van Harmelen
 
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Product School
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Jeffrey Haguewood
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
Dorra BARTAGUIZ
 
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
Product School
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance
 

Recently uploaded (20)

Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
 
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
 
Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
 
Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*
 
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
 
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
 

Cyanapse talk photorealisticf_ilters_migaragemeetup_7nov2018

  • 1. Leveraging machine intelligence to improve sensory experiences Dr Esin Yavuz, Co-founder & Chief Scientist MI Garage Meetup: “How can the creative industries use AI?” 7 November 2018
  • 2. Augmenting sensory perception with machine intelligence Linking machine intelligence and human perception requires real-time and automated image processing. To enable this, we are building a platform that allows fast and automated processing of images using AI.
  • 3. Outline ● Background & State of the art ● AI for photorealistic image transformations ● Automating image editing
  • 4. What is AI? ● “Science of making machines do things that would require intelligence if done by men.” Minsky ● Often used to refer to statistical methods that aim to fnd structure and regularities in data ● Used for making deductions based on observations ● Applied to problem solving, reasoning, natural language processing, machine perception
  • 5.
  • 6. ● 2006: NVIDIA releases CUDA for general purpose GPU computing High-performance computing becomes easier to use ● 2010: ImageNet Large Scale Visual Recognition challenge -Classifcation task based on a dataset of 10M images in 10K+ classes Importance of number of examples and problem defnition ● 2012: Alexnet achieves top-5 error of 15.3%, more than 10.8 percentage points lower than that of the runner up on ImageNet competition using a deep convolutional network Beginning of the Deep Learning era Breakthroughs in the last decade
  • 8. Deep Dream (Google) 2015 ● Initially designed as a tool to understand internal properties of neural networks ● Whatever the network sees, it adjust the other pixels to see more of it ● Allows creative image manipulations based on internal structure of a neural network
  • 9. Neural Style Transfer – Gatys et al. 2016 Combining the content of an image with the style of another image
  • 12. Image generation with Generative Adversarial Nets (GAN) – Goodfellow et al. 2014
  • 13. More recent GAN examples Brock et al - BigGAN (Deepmind) 2018Karras et al. (NVIDIA) 2017 Evolving to be a new tool for artistic creation
  • 14.
  • 15.
  • 17. Artistic style transfer with GAN-based methods Drawbacks ● While artistic style transfer can be easily achieved, photorealistic transformations are not easy ● Mostly support low-res, if not they need massive computational power ● Diffcult to generalise to different content domains
  • 19. Why do we need photorealistic transformations? ● Good quality visual content is indispensable for a better communication through visuals. However, creating good quality visuals needs expertise and it is time consuming. ● Existing tools for image flters provide synthetic results that look similar, most are slow, do not scale for bulk image processing, and still require substantial user expertise. ● Apart from content creation, there is a need in other felds such as data augmentation, video game development, rendering, enhancing video streams.
  • 20. Problems of applying AI to casual photography Flickr/Mr Boss Flickr/Yuma Hori Flickr/Bex Walton
  • 21. AI filers lhal work witlh any l pe of itmages Transform any type of image to refect different daytime lighting conditions
  • 24. AI-powered itmage filers More examples here: cyanapse.com/ai-tech/photorealistic-image-flters
  • 25. ● Use AI-powered photorealistic flters that work with any type of photos ● Automate dull image editing tasks ● Enable bulk image editing with custom pipelines Automated Image Editing Platform 1- Back-end API for fast and automated image processing 2- Front-end App for user-friendly interface
  • 26. ● RESTful API with intuitive endpoints ● Bulk processing that scales to users’ needs ● User-defned image editing pipelines ● Includes AI-enhanced image styling flters Automating image editing
  • 27. Front-end ● Mobile and web app to try out AI flters ● Use AI photo flters in just a few clicks ● Instantaneous generation of various previews ● Less than a second to enhance 4k-res images, 40 ms for a low-res image
  • 28. Advantages ● 4k resolution images are enhanced in less than a second ● AI transformations run in the cloud (fexible and scalable) ● We provide image enhancements that are photorealistic and that work for every type of photos ● Minimise the time spent on creating good quality content, allowing content creators to focus on more important tasks ● Enable real-time and photorealistic enhancements of video streams with minimal human intervention ● Generate multiple possible transformations to help content creators preview the results beforehand, and to pass their messages better
  • 29. Thank you! Email: info@cyanapse.com Register here: cyanapse.com/beta-testing @cyanapse