SlideShare a Scribd company logo
1 of 74
Download to read offline
Raskar, Camera Culture, MIT Media Lab




                                  Future of Imaging &
                                        Idea Hexagon
                                   Camera Culture
                                        Ramesh Raskar
             Ramesh Raskar
             MIT Media Lab
3 Billion Cameras
Mobile Diagnostics                3D TV




Trillion Frames Per Second   Lightfield 3D Camera
Camera in    Movies and        Augmented
 20 years      News              Reality

Pervasive      Health             Print
Recording    Diagnostics        Anything


Photoshop     Trust and            3D
  2032      Social Stability    Displays
How to Invent?

After X, what is neXt
X          neXt
                ?
Share Photos   Share ?
X          neXt


Share Photos   Share Videos
#1:      neXt = Xd
            Generalize to another dimension

      Data  Text  Audio  Images  Video  ..

                 Airbag for car to airbag for .. ?
Stereo Glasses
                 Glasses Free 3D




                      4D
Bandwidth: 1 TB/sec

           1 GB/sec

Compressive Displays
  Wetzstein, Lanman, Hirsch, Raskar, Siggraph 2012
Glasses Free 3D Display
#2:   neXt = X + Y
      Fusion of the Dissimilar
CT-Scan




http://info.med.yale.edu/intmed/cardio/imaging/techniques/ct_imaging/
CT-scan Machine
neXt = X               +        Y
                                   Space
Portable CT   =   CT Machine +
                                 Telescope
X      X+Y

                d
X   neXt       X

    X++    X
#3:    neXt = X
      Given a hammer, find all the nails
First Roll of Film
Trillion Frames per Second

      Femto-Photography

           Light in Motion
Light in Slow Motion ..




          10 Billion x Slow
raskar.info/trillionfps
Can you see
around corners ?
2nd Bounce




              1st Bounce

 3rd Bounce
Hidden
Femto-Camera                        Mannequin

                    Wall
                                      Door
        Velten et al, Nature Communications 2012
Avoiding Collisions




 Andreas Velten, Thomas Willwacher, Otkrist Gupta, Ashok Veeraraghavan,
          Moungi Bawendi, Ramesh Raskar, Nature Communications 2012
…, rescue operations, …




Rohit Pandharkar, Velten, Bardagjy, Lawson, Bawendi, Raskar, CVPR 2011
…, endoscopies, …
#3:     neXt = X
      Given a hammer, find all the nails
                            + screws and bolts

         App Store .. open platform .. ?
#4:     neXt = X
      Given a nail, find all the hammers
Digital Refocusing




 Lytro: Lightfield Camera
Fernald, Science 2006
Mask based Light Field Camera
                                                                Sensor
                                                        Mask




Larval Trematode Worm




         [Veeraraghavan, Raskar, Agrawal, Tumblin, Mohan, Siggraph 2007 ]
X      X+Y
                         Beyond
                d
X   neXt       X    Technology ..


    X++    X
#5:   neXt = X++
             X + Adjective
Adaptive              Distributed

     Hierarchical

  Efficient
                    Parallelized
                                     Green

                    Social
Democratized
                                     Open
                      Personalized
#6:   neXt = X
      Do exactly the opposite
Fosbury Flop



http://en.wikipedia.org/wiki/File:Bundesarchiv_Bild_183-S0305-0030,_Rolf_Beilschmidt.jpg




            Straddle Method                                             Foam Rubber        Fosbury Method
                                                                                             1968 Olympic Gold
                                                                                           http://en.wikipedia.org/wiki/Dick_Fosbury
300+ DPI LCDs
Slit Lamp for
  Cataracts
Retinal
 Scan




          Slit Lamp Exam   Retinal Scan




                                          41
Phoropter




            Reading Charts
eyeNETRA:
  Glasses and Cataract




Pamplona, Mohan, Oliveira, Raskar SIGGRAPH 2010
0.6B without
                  2B           glasses
              refractive
                errors


    4.5B
cell phones




                           7 Billion             NETRA at
                                           LVP Eye Institute
                           people
Diagnostics                       Dispensing Glasses




Bulky Equipment , Trained Professionals     Increasingly cheap and easy
Refraction Map using Wavefront Sensor




Wavefront aberrometer




                        Shack-Hartmann WS
NETRA = Inverse of Shack-Hartmann wavefront sensor
             User interactively creates the Spot Diagram
Spot Diagram CellPhone
   on LCD        LCD                                 2. Displace spots
                                                       till single dot
                                                         perceived



1. Displace 25           EyePiece
  spots with
   smart UI

                                                               47
Kenya




Thermometer for Eye
                48
India
Brazil
NETRA Worldwide




     Confidential   51
Photo of women and weighing scale




                           Entrepreneur
neXt
Raskar 2012, Idea Hexagon

More Related Content

What's hot

Large Language Models - Chat AI.pdf
Large Language Models - Chat AI.pdfLarge Language Models - Chat AI.pdf
Large Language Models - Chat AI.pdfDavid Rostcheck
 
‘Big models’: the success and pitfalls of Transformer models in natural langu...
‘Big models’: the success and pitfalls of Transformer models in natural langu...‘Big models’: the success and pitfalls of Transformer models in natural langu...
‘Big models’: the success and pitfalls of Transformer models in natural langu...Leiden University
 
Leveraging Generative AI & Best practices
Leveraging Generative AI & Best practicesLeveraging Generative AI & Best practices
Leveraging Generative AI & Best practicesDianaGray10
 
Responsible Generative AI
Responsible Generative AIResponsible Generative AI
Responsible Generative AICMassociates
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual IntroductionLukas Masuch
 
Introduction to LLMs
Introduction to LLMsIntroduction to LLMs
Introduction to LLMsLoic Merckel
 
Data Con LA 2022 - Transformers for NLP
Data Con LA 2022 - Transformers for NLPData Con LA 2022 - Transformers for NLP
Data Con LA 2022 - Transformers for NLPData Con LA
 
Fine tuning large LMs
Fine tuning large LMsFine tuning large LMs
Fine tuning large LMsSylvainGugger
 
Metaverse_SGAsia2022.pdf
Metaverse_SGAsia2022.pdfMetaverse_SGAsia2022.pdf
Metaverse_SGAsia2022.pdfWoontack Woo
 
ChatGPT, Foundation Models and Web3.pptx
ChatGPT, Foundation Models and Web3.pptxChatGPT, Foundation Models and Web3.pptx
ChatGPT, Foundation Models and Web3.pptxJesus Rodriguez
 
Reinventing Deep Learning
 with Hugging Face Transformers
Reinventing Deep Learning
 with Hugging Face TransformersReinventing Deep Learning
 with Hugging Face Transformers
Reinventing Deep Learning
 with Hugging Face TransformersJulien SIMON
 
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...Edureka!
 
An introduction to computer vision with Hugging Face
An introduction to computer vision with Hugging FaceAn introduction to computer vision with Hugging Face
An introduction to computer vision with Hugging FaceJulien SIMON
 
Introduction to AIoT & TinyML - with Arduino
Introduction to AIoT & TinyML - with ArduinoIntroduction to AIoT & TinyML - with Arduino
Introduction to AIoT & TinyML - with ArduinoAndri Yadi
 
Generative AI and law.pptx
Generative AI and law.pptxGenerative AI and law.pptx
Generative AI and law.pptxChris Marsden
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial IntelligenceNeil Mathew
 
Generative-AI-in-enterprise-20230615.pdf
Generative-AI-in-enterprise-20230615.pdfGenerative-AI-in-enterprise-20230615.pdf
Generative-AI-in-enterprise-20230615.pdfLiming Zhu
 
How ChatGPT and AI-assisted coding changes software engineering profoundly
How ChatGPT and AI-assisted coding changes software engineering profoundlyHow ChatGPT and AI-assisted coding changes software engineering profoundly
How ChatGPT and AI-assisted coding changes software engineering profoundlyPekka Abrahamsson / Tampere University
 

What's hot (20)

Raskar Entrepreneurship in Imaging, Imaging Ventures, CVPR 2012
Raskar Entrepreneurship in Imaging, Imaging Ventures, CVPR 2012Raskar Entrepreneurship in Imaging, Imaging Ventures, CVPR 2012
Raskar Entrepreneurship in Imaging, Imaging Ventures, CVPR 2012
 
Large Language Models - Chat AI.pdf
Large Language Models - Chat AI.pdfLarge Language Models - Chat AI.pdf
Large Language Models - Chat AI.pdf
 
‘Big models’: the success and pitfalls of Transformer models in natural langu...
‘Big models’: the success and pitfalls of Transformer models in natural langu...‘Big models’: the success and pitfalls of Transformer models in natural langu...
‘Big models’: the success and pitfalls of Transformer models in natural langu...
 
Leveraging Generative AI & Best practices
Leveraging Generative AI & Best practicesLeveraging Generative AI & Best practices
Leveraging Generative AI & Best practices
 
Responsible Generative AI
Responsible Generative AIResponsible Generative AI
Responsible Generative AI
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual Introduction
 
Introduction to LLMs
Introduction to LLMsIntroduction to LLMs
Introduction to LLMs
 
Data Con LA 2022 - Transformers for NLP
Data Con LA 2022 - Transformers for NLPData Con LA 2022 - Transformers for NLP
Data Con LA 2022 - Transformers for NLP
 
Open AI Chat GPT.
Open AI Chat GPT.Open AI Chat GPT.
Open AI Chat GPT.
 
Fine tuning large LMs
Fine tuning large LMsFine tuning large LMs
Fine tuning large LMs
 
Metaverse_SGAsia2022.pdf
Metaverse_SGAsia2022.pdfMetaverse_SGAsia2022.pdf
Metaverse_SGAsia2022.pdf
 
ChatGPT, Foundation Models and Web3.pptx
ChatGPT, Foundation Models and Web3.pptxChatGPT, Foundation Models and Web3.pptx
ChatGPT, Foundation Models and Web3.pptx
 
Reinventing Deep Learning
 with Hugging Face Transformers
Reinventing Deep Learning
 with Hugging Face TransformersReinventing Deep Learning
 with Hugging Face Transformers
Reinventing Deep Learning
 with Hugging Face Transformers
 
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...
 
An introduction to computer vision with Hugging Face
An introduction to computer vision with Hugging FaceAn introduction to computer vision with Hugging Face
An introduction to computer vision with Hugging Face
 
Introduction to AIoT & TinyML - with Arduino
Introduction to AIoT & TinyML - with ArduinoIntroduction to AIoT & TinyML - with Arduino
Introduction to AIoT & TinyML - with Arduino
 
Generative AI and law.pptx
Generative AI and law.pptxGenerative AI and law.pptx
Generative AI and law.pptx
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
 
Generative-AI-in-enterprise-20230615.pdf
Generative-AI-in-enterprise-20230615.pdfGenerative-AI-in-enterprise-20230615.pdf
Generative-AI-in-enterprise-20230615.pdf
 
How ChatGPT and AI-assisted coding changes software engineering profoundly
How ChatGPT and AI-assisted coding changes software engineering profoundlyHow ChatGPT and AI-assisted coding changes software engineering profoundly
How ChatGPT and AI-assisted coding changes software engineering profoundly
 

Viewers also liked

How to come up with new research ideas
How to come up with new research ideasHow to come up with new research ideas
How to come up with new research ideasJia-Bin Huang
 
Richard Matthew Stallman - A Brief Biography
Richard Matthew Stallman - A Brief BiographyRichard Matthew Stallman - A Brief Biography
Richard Matthew Stallman - A Brief BiographyHackerEarth
 
About DevFactory
About DevFactory About DevFactory
About DevFactory HackerEarth
 
Recent Advances in Computer Vision
Recent Advances in Computer VisionRecent Advances in Computer Vision
Recent Advances in Computer Visionantiw
 
Evolution or Innovation
Evolution or InnovationEvolution or Innovation
Evolution or InnovationLifelog Health
 
Matrix Factorisation (and Dimensionality Reduction)
Matrix Factorisation (and Dimensionality Reduction)Matrix Factorisation (and Dimensionality Reduction)
Matrix Factorisation (and Dimensionality Reduction)HJ van Veen
 
How to become a Data Scientist?
How to become a Data Scientist? How to become a Data Scientist?
How to become a Data Scientist? HackerEarth
 
How to Read Academic Papers
How to Read Academic PapersHow to Read Academic Papers
How to Read Academic PapersJia-Bin Huang
 
What Makes a Creative Photograph?
What Makes a Creative Photograph?What Makes a Creative Photograph?
What Makes a Creative Photograph?Jia-Bin Huang
 
Computer Vision Crash Course
Computer Vision Crash CourseComputer Vision Crash Course
Computer Vision Crash CourseJia-Bin Huang
 
Writing Fast MATLAB Code
Writing Fast MATLAB CodeWriting Fast MATLAB Code
Writing Fast MATLAB CodeJia-Bin Huang
 
Research 101 - Paper Writing with LaTeX
Research 101 - Paper Writing with LaTeXResearch 101 - Paper Writing with LaTeX
Research 101 - Paper Writing with LaTeXJia-Bin Huang
 
How to Win Machine Learning Competitions ?
How to Win Machine Learning Competitions ? How to Win Machine Learning Competitions ?
How to Win Machine Learning Competitions ? HackerEarth
 

Viewers also liked (13)

How to come up with new research ideas
How to come up with new research ideasHow to come up with new research ideas
How to come up with new research ideas
 
Richard Matthew Stallman - A Brief Biography
Richard Matthew Stallman - A Brief BiographyRichard Matthew Stallman - A Brief Biography
Richard Matthew Stallman - A Brief Biography
 
About DevFactory
About DevFactory About DevFactory
About DevFactory
 
Recent Advances in Computer Vision
Recent Advances in Computer VisionRecent Advances in Computer Vision
Recent Advances in Computer Vision
 
Evolution or Innovation
Evolution or InnovationEvolution or Innovation
Evolution or Innovation
 
Matrix Factorisation (and Dimensionality Reduction)
Matrix Factorisation (and Dimensionality Reduction)Matrix Factorisation (and Dimensionality Reduction)
Matrix Factorisation (and Dimensionality Reduction)
 
How to become a Data Scientist?
How to become a Data Scientist? How to become a Data Scientist?
How to become a Data Scientist?
 
How to Read Academic Papers
How to Read Academic PapersHow to Read Academic Papers
How to Read Academic Papers
 
What Makes a Creative Photograph?
What Makes a Creative Photograph?What Makes a Creative Photograph?
What Makes a Creative Photograph?
 
Computer Vision Crash Course
Computer Vision Crash CourseComputer Vision Crash Course
Computer Vision Crash Course
 
Writing Fast MATLAB Code
Writing Fast MATLAB CodeWriting Fast MATLAB Code
Writing Fast MATLAB Code
 
Research 101 - Paper Writing with LaTeX
Research 101 - Paper Writing with LaTeXResearch 101 - Paper Writing with LaTeX
Research 101 - Paper Writing with LaTeX
 
How to Win Machine Learning Competitions ?
How to Win Machine Learning Competitions ? How to Win Machine Learning Competitions ?
How to Win Machine Learning Competitions ?
 

Similar to Raskar 2012, Idea Hexagon

MetatonZ: Troyer Patents Elevator uptodate 60614
MetatonZ: Troyer Patents Elevator uptodate 60614MetatonZ: Troyer Patents Elevator uptodate 60614
MetatonZ: Troyer Patents Elevator uptodate 60614Diane Troyer
 
Raskar Emtech2010 Mar Final
Raskar Emtech2010 Mar FinalRaskar Emtech2010 Mar Final
Raskar Emtech2010 Mar FinalEmTech
 
Metatroy Z*TV patents blogs Nov. 2011 - June 2012
Metatroy Z*TV patents blogs Nov. 2011 - June 2012 Metatroy Z*TV patents blogs Nov. 2011 - June 2012
Metatroy Z*TV patents blogs Nov. 2011 - June 2012 Diane Troyer
 
Making Invisible Visible, Ramesh Raskar Keynote at Embedded Vision 2019
Making Invisible Visible, Ramesh Raskar Keynote at Embedded Vision 2019Making Invisible Visible, Ramesh Raskar Keynote at Embedded Vision 2019
Making Invisible Visible, Ramesh Raskar Keynote at Embedded Vision 2019Camera Culture Group, MIT Media Lab
 
"Making the Invisible Visible: Within Our Bodies, the World Around Us and Bey...
"Making the Invisible Visible: Within Our Bodies, the World Around Us and Bey..."Making the Invisible Visible: Within Our Bodies, the World Around Us and Bey...
"Making the Invisible Visible: Within Our Bodies, the World Around Us and Bey...Edge AI and Vision Alliance
 
3 d body scanning
3 d body scanning3 d body scanning
3 d body scanningArka Das
 
Humanizing bioinformatics
Humanizing bioinformaticsHumanizing bioinformatics
Humanizing bioinformaticsJan Aerts
 
뇌인지과학과 뇌질환 원인규명 및 치료법 연구 ;
뇌인지과학과 뇌질환 원인규명 및 치료법 연구 ; 뇌인지과학과 뇌질환 원인규명 및 치료법 연구 ;
뇌인지과학과 뇌질환 원인규명 및 치료법 연구 ; Namkug Kim
 
University of florida 3 d lapidary scanner 110614
University of florida 3 d lapidary scanner 110614University of florida 3 d lapidary scanner 110614
University of florida 3 d lapidary scanner 110614Robert Harker
 
Grand Challenges for Mixed Reality
Grand Challenges for Mixed Reality Grand Challenges for Mixed Reality
Grand Challenges for Mixed Reality Mark Billinghurst
 
Raskar, Rank and Sparsity in Computational Photography and Computational Ligh...
Raskar, Rank and Sparsity in Computational Photography and Computational Ligh...Raskar, Rank and Sparsity in Computational Photography and Computational Ligh...
Raskar, Rank and Sparsity in Computational Photography and Computational Ligh...Camera Culture Group, MIT Media Lab
 
"Think Like an Amateur, Do As an Expert: Lessons from a Career in Computer Vi...
"Think Like an Amateur, Do As an Expert: Lessons from a Career in Computer Vi..."Think Like an Amateur, Do As an Expert: Lessons from a Career in Computer Vi...
"Think Like an Amateur, Do As an Expert: Lessons from a Career in Computer Vi...Edge AI and Vision Alliance
 

Similar to Raskar 2012, Idea Hexagon (20)

MetatonZ: Troyer Patents Elevator uptodate 60614
MetatonZ: Troyer Patents Elevator uptodate 60614MetatonZ: Troyer Patents Elevator uptodate 60614
MetatonZ: Troyer Patents Elevator uptodate 60614
 
Raskar Emtech2010 Mar Final
Raskar Emtech2010 Mar FinalRaskar Emtech2010 Mar Final
Raskar Emtech2010 Mar Final
 
Raskar Emtech2010 Mar Final
Raskar Emtech2010 Mar FinalRaskar Emtech2010 Mar Final
Raskar Emtech2010 Mar Final
 
Metatroy Z*TV patents blogs Nov. 2011 - June 2012
Metatroy Z*TV patents blogs Nov. 2011 - June 2012 Metatroy Z*TV patents blogs Nov. 2011 - June 2012
Metatroy Z*TV patents blogs Nov. 2011 - June 2012
 
Raskar Computational Camera Fall 2009 Lecture 01
Raskar Computational Camera Fall 2009 Lecture 01Raskar Computational Camera Fall 2009 Lecture 01
Raskar Computational Camera Fall 2009 Lecture 01
 
Augmented Surgeons: AI AR for Anatome, Raskar Aria 2019
Augmented Surgeons: AI AR for Anatome, Raskar Aria 2019Augmented Surgeons: AI AR for Anatome, Raskar Aria 2019
Augmented Surgeons: AI AR for Anatome, Raskar Aria 2019
 
Making Invisible Visible, Ramesh Raskar Keynote at Embedded Vision 2019
Making Invisible Visible, Ramesh Raskar Keynote at Embedded Vision 2019Making Invisible Visible, Ramesh Raskar Keynote at Embedded Vision 2019
Making Invisible Visible, Ramesh Raskar Keynote at Embedded Vision 2019
 
"Making the Invisible Visible: Within Our Bodies, the World Around Us and Bey...
"Making the Invisible Visible: Within Our Bodies, the World Around Us and Bey..."Making the Invisible Visible: Within Our Bodies, the World Around Us and Bey...
"Making the Invisible Visible: Within Our Bodies, the World Around Us and Bey...
 
Photonics bretagne members
Photonics bretagne membersPhotonics bretagne members
Photonics bretagne members
 
Report
ReportReport
Report
 
CI image processing
CI image processing CI image processing
CI image processing
 
3 d body scanning
3 d body scanning3 d body scanning
3 d body scanning
 
Humanizing bioinformatics
Humanizing bioinformaticsHumanizing bioinformatics
Humanizing bioinformatics
 
Augmented reality
Augmented realityAugmented reality
Augmented reality
 
뇌인지과학과 뇌질환 원인규명 및 치료법 연구 ;
뇌인지과학과 뇌질환 원인규명 및 치료법 연구 ; 뇌인지과학과 뇌질환 원인규명 및 치료법 연구 ;
뇌인지과학과 뇌질환 원인규명 및 치료법 연구 ;
 
University of florida 3 d lapidary scanner 110614
University of florida 3 d lapidary scanner 110614University of florida 3 d lapidary scanner 110614
University of florida 3 d lapidary scanner 110614
 
Grand Challenges for Mixed Reality
Grand Challenges for Mixed Reality Grand Challenges for Mixed Reality
Grand Challenges for Mixed Reality
 
Raskar, Rank and Sparsity in Computational Photography and Computational Ligh...
Raskar, Rank and Sparsity in Computational Photography and Computational Ligh...Raskar, Rank and Sparsity in Computational Photography and Computational Ligh...
Raskar, Rank and Sparsity in Computational Photography and Computational Ligh...
 
Unspoken Challenges in AR and XR
Unspoken Challenges in AR and XRUnspoken Challenges in AR and XR
Unspoken Challenges in AR and XR
 
"Think Like an Amateur, Do As an Expert: Lessons from a Career in Computer Vi...
"Think Like an Amateur, Do As an Expert: Lessons from a Career in Computer Vi..."Think Like an Amateur, Do As an Expert: Lessons from a Career in Computer Vi...
"Think Like an Amateur, Do As an Expert: Lessons from a Career in Computer Vi...
 

More from Camera Culture Group, MIT Media Lab

God’s Eye View: Will global AI empower us or destroy us? | Ramesh Raskar
God’s Eye View: Will global AI empower us or destroy us? | Ramesh Raskar God’s Eye View: Will global AI empower us or destroy us? | Ramesh Raskar
God’s Eye View: Will global AI empower us or destroy us? | Ramesh Raskar Camera Culture Group, MIT Media Lab
 
Dont follow the rainbow: How to avoid career traps that can lead you to fail,...
Dont follow the rainbow: How to avoid career traps that can lead you to fail,...Dont follow the rainbow: How to avoid career traps that can lead you to fail,...
Dont follow the rainbow: How to avoid career traps that can lead you to fail,...Camera Culture Group, MIT Media Lab
 
Split Learning versus Federated Learning for Data Transparent ML, Camera Cult...
Split Learning versus Federated Learning for Data Transparent ML, Camera Cult...Split Learning versus Federated Learning for Data Transparent ML, Camera Cult...
Split Learning versus Federated Learning for Data Transparent ML, Camera Cult...Camera Culture Group, MIT Media Lab
 

More from Camera Culture Group, MIT Media Lab (20)

Raskar Sig2017 Siggraph Achievement Award Talk
Raskar Sig2017 Siggraph Achievement Award TalkRaskar Sig2017 Siggraph Achievement Award Talk
Raskar Sig2017 Siggraph Achievement Award Talk
 
Lost Decade of Computational Photography
Lost Decade of Computational PhotographyLost Decade of Computational Photography
Lost Decade of Computational Photography
 
Covid Safe Paths
Covid Safe PathsCovid Safe Paths
Covid Safe Paths
 
God’s Eye View: Will global AI empower us or destroy us? | Ramesh Raskar
God’s Eye View: Will global AI empower us or destroy us? | Ramesh Raskar God’s Eye View: Will global AI empower us or destroy us? | Ramesh Raskar
God’s Eye View: Will global AI empower us or destroy us? | Ramesh Raskar
 
Dont follow the rainbow: How to avoid career traps that can lead you to fail,...
Dont follow the rainbow: How to avoid career traps that can lead you to fail,...Dont follow the rainbow: How to avoid career traps that can lead you to fail,...
Dont follow the rainbow: How to avoid career traps that can lead you to fail,...
 
Raskar PhD and MS Thesis Guidance
Raskar PhD and MS Thesis GuidanceRaskar PhD and MS Thesis Guidance
Raskar PhD and MS Thesis Guidance
 
Geo-spatial Research: Transition from Analysis to Synthesis
Geo-spatial Research: Transition from Analysis to SynthesisGeo-spatial Research: Transition from Analysis to Synthesis
Geo-spatial Research: Transition from Analysis to Synthesis
 
Split Learning versus Federated Learning for Data Transparent ML, Camera Cult...
Split Learning versus Federated Learning for Data Transparent ML, Camera Cult...Split Learning versus Federated Learning for Data Transparent ML, Camera Cult...
Split Learning versus Federated Learning for Data Transparent ML, Camera Cult...
 
Raskar stanfordextremecompuimagingapr2016
Raskar stanfordextremecompuimagingapr2016Raskar stanfordextremecompuimagingapr2016
Raskar stanfordextremecompuimagingapr2016
 
What is SIGGRAPH NEXT? Intro by Ramesh Raskar
What is SIGGRAPH NEXT? Intro by Ramesh RaskarWhat is SIGGRAPH NEXT? Intro by Ramesh Raskar
What is SIGGRAPH NEXT? Intro by Ramesh Raskar
 
Raskar UIST Keynote 2015 November
Raskar UIST Keynote 2015 NovemberRaskar UIST Keynote 2015 November
Raskar UIST Keynote 2015 November
 
Multiview Imaging HW Overview
Multiview Imaging HW OverviewMultiview Imaging HW Overview
Multiview Imaging HW Overview
 
Time of Flight Cameras - Refael Whyte
Time of Flight Cameras - Refael WhyteTime of Flight Cameras - Refael Whyte
Time of Flight Cameras - Refael Whyte
 
Leap Motion Development (Rohan Puri)
Leap Motion Development (Rohan Puri)Leap Motion Development (Rohan Puri)
Leap Motion Development (Rohan Puri)
 
Compressed Sensing - Achuta Kadambi
Compressed Sensing - Achuta KadambiCompressed Sensing - Achuta Kadambi
Compressed Sensing - Achuta Kadambi
 
Coded Photography - Ramesh Raskar
Coded Photography - Ramesh RaskarCoded Photography - Ramesh Raskar
Coded Photography - Ramesh Raskar
 
Stereo and 3D Displays - Matt Hirsch
Stereo and 3D Displays - Matt HirschStereo and 3D Displays - Matt Hirsch
Stereo and 3D Displays - Matt Hirsch
 
Introduction to Camera Challenges - Ramesh Raskar
Introduction to Camera Challenges - Ramesh RaskarIntroduction to Camera Challenges - Ramesh Raskar
Introduction to Camera Challenges - Ramesh Raskar
 
Developing "True HDR" for the iPhone
Developing "True HDR" for the iPhoneDeveloping "True HDR" for the iPhone
Developing "True HDR" for the iPhone
 
Computer Vision Introduction
Computer Vision IntroductionComputer Vision Introduction
Computer Vision Introduction
 

Raskar 2012, Idea Hexagon

Editor's Notes

  1. Six ways of coming up with new ideas based on an idea ‘X’.Ramesh RaskarAssociate ProfessorMIT Media Labhttp://raskar.infohttp://cameraculture.infohttp://raskar.infohttp://cameraculture.info
  2. Six ways of coming up with new ideas based on an idea ‘X’.Ramesh RaskarAssociate ProfessorMIT Media Labhttp://raskar.infohttp://cameraculture.infohttp://raskar.infohttp://cameraculture.info
  3. Six ways of coming up with new ideas based on an idea ‘X’.Ramesh RaskarAssociate ProfessorMIT Media Labhttp://raskar.infohttp://cameraculture.infohttp://raskar.infohttp://cameraculture.info
  4. Six ways of coming up with new ideas based on an idea ‘X’.Ramesh RaskarAssociate ProfessorMIT Media Labhttp://raskar.infohttp://cameraculture.infohttp://raskar.infohttp://cameraculture.info
  5. Lets start with a simple exercise ..X up: Airbags for car, for helicopter
  6. Lets start with a simple exercise ..X up: Airbags for car, for helicopter
  7. Lets start with a simple exercise ..X up: Airbags for car, for helicopter
  8. Lets start with a simple exercise ..X up: Airbags for car, for helicopter
  9. Lets start with a simple exercise ..X up: Airbags for car, for helicopter
  10. Lets start with a simple exercise ..X up: Airbags for car, for helicopter
  11. My Photo24 roll film for one year
  12. Create videos at m, b, trillion fpsI introduce new type of photography.. Femto photographyTechnique so fat .. Slow motion videos of light in motWith that, LaC, see inside our body without xraysChallenge our notion of a cameraTo record bullets of LIGHT passing thru the world .. And remember light travels nearly a million times faster than an ordinary bulletSo what is femto-photographyNot just for visual aestheticsCamera that can look around cornersUltrasound with light to look under the skin inside our bodies
  13. What if we send this bullet of photons to shatter into this bottleHow does light look in slow motionThe whole sequence is less than a nanosecond stretched to about 10 seconds i.e. 10 billion times slowed downIf an oridinary bullet,same distance at such a slow motion video, do you know how long you will have to sit here to watch the movie? A day, a week .. a whole year .. it will be a very boring movie .. Clean_coke_mulSlow2v1.mov
  14. Superman can fly and heroes can becomes invisible .. But what about a new power for a future super-hero ..To see around corners ..
  15. The idea is to use echoes of light .. Multiple bounces .. We send flash light with our femto-camera to the door, part of it scatters into the room A small fraction comes back to the door and even tinier fraction comes back to our femto-cameraBy analyzing these multiply bounced photos with trillion frames per second imaging, it turns out we can look around corners beyond the line of sight========Echoes of sound -> Echoes of light
  16. Not just science fiction but we have actually shown this in our lab on a tabletop setupThe femto-camera is on the left and the mannequin is hidden behind the wall .. so how do we do it? Our paper was recently published and highlighted on nature.com and Nature produced this animation
  17. We can create cars that avoid collion with what is around the bend ..
  18. Or look for survivors in hazardous conditions from changes in light reflected from open windows
  19. And to see deep inside the body with endoscopes that look in narrow channels in lungs Or colonsColonoscopy/cardioscopy
  20. Given a cool solution/technique/Opportunity Find other problems(Where to find them?)
  21. Given a problem, Find other solutions(Where to find them?)
  22. Faster better cheaper
  23. Add your favorite adjectiveWikipedia is encyclopedia democratizedFacebook is Pandora is radio personalized
  24. Given a problem, Find other solutions(Where to find them?)
  25. Straddle method for high jumpReplacement of landing surfaces with foam rubberFosbury Method1968 Olympics: 2.24m
  26. This is mobile phones today but was not possible even 3 years agoThe reason is phone makers are rapidly increasing the resolution of the screens Why because we all want to watch out favorite episodes in HDThe pixel pitch is now down to about 25 micrometers, half the width of a human hairAt that resolution we can cleverly exploit the phone as a scientific instrumentSo pl go and watch more HD content and play HD games and help build the next mobile diagnostic device
  27. Bulky, expensive , trained professionalsHere is a cataract exam with a slit lamp .. A device that hasn’t really changed for decades
  28. And here getting a retinal scan .. But checkout the user interface .. It is a quarter million dollar device but the nurse has to shove my head into the eyepiece
  29. And here to get eyeglasses, I am lost in a phoropter.This diagnostics while a fine solution in developed countries is not going to scale in developing countries lack of diagnostics .. Millions worldwide are suffering from conditions that have proven treatmentsReading charts appear to be an easy solution, this method has too many problems. Sharpness of legible text is very subjective. The brightness of the chart has to be very carefully chosen otherwise the pupil size will change, increasing depth of field, and allowing user to recognize even lower rows.The trial lenses + the lens frame the doctor will use also cost over $150% Reading chart tests involve using a frame or a phoropter. The doctor will swing a sequence of lenses in front of your eye and ask for which lens allows you to see the lower rows on the reading chart.
  30. ImagineWe call our tool NETRA: a one dollar clip on eye piece that goes on top a cellphonenear eye tool for refractive assessmentsuch as nearsightedness/far/astigmatism
  31. 2 billion people have refractive errorsAnd half a billion mostly in developing countries worldwide have uncorrected vision that affects their daily livelihood. Country like India only 10K optometrists for 1B people, and many smaller countries no optometrists at allBlurry vision leads to illiteracy, unemployement and povertyMore phones that toothbrushes and people who make less than a dollarThey don’t have access to an optometrist or it simply too expensive. While making and distributing of lenses has become quite easy now, surprisingly there is still no easy solution for measuring eyesight.Can we use a fraction of the 4.5B cellphone displays to address this problem?
  32. There are two pieces to the puzzle of providing eyeglassesDiagnostics and dispensing. Over time, the cost of providing eyeglasses has come down dramatically and this shop here in Mumbai can sell distant vision glasses for under $3 and still make profits. But there is still no easy solution for diagnosis .. Country like India only 10K optometrists for 1B people, and many smaller countries no optometrists at allWhile making and distributing of lenses has become quite easy now, surprisingly there is still no easy solution for measuring eyesight.Can we use a fraction of the 4.5B cellphone displays to address this problem?
  33. The most accurate method is based on a so called SH WS that you would use to get a refraction map before a Lasik surgery. I love this kind of stuff.My group at MIT Media Lab invents crazy cameras and displays: a camera that can look around corners beyond the line of sight that costs a million dollars, a portable CAT scan machine, glasses free 3D displays .. But every once a while I like to boil down all the mathematics, optics and theory into something really modest that costs just a dollarNetra is actually exactly opposite of this complicated laser based sensor============It involves shining a laser at the back of the retina and observing the wavefront using a sophisticated sensor.We ask user to generate a spot diagram. But navigating in a high dimensional space ischallenging so we come up with a strikingly simple approach to let the user interactively create the spotdiagram.We are first to make connection between Shack Hartmann and Lightfields (and it goes well with recentwork in computational photography about ALF and Zhang/Levoy). Connection to Adaptive optics/Astronomy. The way that this device works is that, it shines a lasers in the eye, the laser is reflected in the retina and comes out of the eye being distorted by the cornea. These light rays reaches an array of lenses that focus them to dots in a sensor. The device measures how much this dots deviate from the ideal case. Since it uses lasers, the device is expensive and requires trained professionals
  34. We ask the user to manipulate patterns on the LCD screen so that the user perceives only a single dot at the end.The number of clicks it takes to align in each directions gives us your complete spherical and cylindrical parameters==============Netra is based on a light wavefront sensor but acting in reverse.A traditional wavefront sensor, called Shack Hartmann sensor involves shining lasers into the eye and using a high quality detector to record reflected light.Netra is basically the inverse of such wavefront sensor. We ask the user to manipulate patterns on the LCD screen so that the user perceives only a single dot at the end.For eye with distortion, the user will interactively displace the 25 points so that he will see a single spot. Of course changing 25 spot locations is cumbersome, but we realize that there are only 3 parameters for eye-prescription and we help the user navigate thru this space efficiently.But if you think about these theory, you will realize that we have the dual of the shack-hartmann. First we though out the laser.
  35. Blurry vision is not life threatening but often gets overlookedWe can give children a shot at decent education with early diagnosticsIn that sense, Netra is a thermometer for the eye, and one can check regularly as the child is growing upVideo game
  36. Vision is important for day labor for his employment
  37. And sometimes its just that important to be able to watch Ronaldinho kick that soccer goal
  38. Thanks to the portable, no mechanically moving parts, and low cost, we have received a tremendous response in a very short time. Netra is working with NGOs in more than a dozen countries, collaborating with eyeclinics, research centers and glasses-makers. Plus multiple IRB approved trials.And as a professor what delights me is that my students are writing a series of prestigious academic papers in the geekiest of journals
  39. Integrating optics, computer graphics and interactive techniques can address this worldwide problem.So, because NETRA and CATRA are portable, low-cost, and easy to build and use, we created an initiative called EyeNETRA.com to spread these hardware apps. We aim to increase the accessibility for eye care in remote parts of the world.These hardware apps will empower millions of people through patient centric ecosystems that start with diagnosis and awareness.
  40. Integrating optics, computer graphics and interactive techniques can address this worldwide problem.So, because NETRA and CATRA are portable, low-cost, and easy to build and use, we created an initiative called EyeNETRA.com to spread these hardware apps. We aim to increase the accessibility for eye care in remote parts of the world.These hardware apps will empower millions of people through patient centric ecosystems that start with diagnosis and awareness.
  41. Integrating optics, computer graphics and interactive techniques can address this worldwide problem.So, because NETRA and CATRA are portable, low-cost, and easy to build and use, we created an initiative called EyeNETRA.com to spread these hardware apps. We aim to increase the accessibility for eye care in remote parts of the world.These hardware apps will empower millions of people through patient centric ecosystems that start with diagnosis and awareness.
  42. Integrating optics, computer graphics and interactive techniques can address this worldwide problem.So, because NETRA and CATRA are portable, low-cost, and easy to build and use, we created an initiative called EyeNETRA.com to spread these hardware apps. We aim to increase the accessibility for eye care in remote parts of the world.These hardware apps will empower millions of people through patient centric ecosystems that start with diagnosis and awareness.
  43. Integrating optics, computer graphics and interactive techniques can address this worldwide problem.So, because NETRA and CATRA are portable, low-cost, and easy to build and use, we created an initiative called EyeNETRA.com to spread these hardware apps. We aim to increase the accessibility for eye care in remote parts of the world.These hardware apps will empower millions of people through patient centric ecosystems that start with diagnosis and awareness.
  44. Integrating optics, computer graphics and interactive techniques can address this worldwide problem.So, because NETRA and CATRA are portable, low-cost, and easy to build and use, we created an initiative called EyeNETRA.com to spread these hardware apps. We aim to increase the accessibility for eye care in remote parts of the world.These hardware apps will empower millions of people through patient centric ecosystems that start with diagnosis and awareness.
  45. Integrating optics, computer graphics and interactive techniques can address this worldwide problem.So, because NETRA and CATRA are portable, low-cost, and easy to build and use, we created an initiative called EyeNETRA.com to spread these hardware apps. We aim to increase the accessibility for eye care in remote parts of the world.These hardware apps will empower millions of people through patient centric ecosystems that start with diagnosis and awareness.
  46. Integrating optics, computer graphics and interactive techniques can address this worldwide problem.So, because NETRA and CATRA are portable, low-cost, and easy to build and use, we created an initiative called EyeNETRA.com to spread these hardware apps. We aim to increase the accessibility for eye care in remote parts of the world.These hardware apps will empower millions of people through patient centric ecosystems that start with diagnosis and awareness.
  47. Integrating optics, computer graphics and interactive techniques can address this worldwide problem.So, because NETRA and CATRA are portable, low-cost, and easy to build and use, we created an initiative called EyeNETRA.com to spread these hardware apps. We aim to increase the accessibility for eye care in remote parts of the world.These hardware apps will empower millions of people through patient centric ecosystems that start with diagnosis and awareness.
  48. Integrating optics, computer graphics and interactive techniques can address this worldwide problem.So, because NETRA and CATRA are portable, low-cost, and easy to build and use, we created an initiative called EyeNETRA.com to spread these hardware apps. We aim to increase the accessibility for eye care in remote parts of the world.These hardware apps will empower millions of people through patient centric ecosystems that start with diagnosis and awareness.
  49. Integrating optics, computer graphics and interactive techniques can address this worldwide problem.So, because NETRA and CATRA are portable, low-cost, and easy to build and use, we created an initiative called EyeNETRA.com to spread these hardware apps. We aim to increase the accessibility for eye care in remote parts of the world.These hardware apps will empower millions of people through patient centric ecosystems that start with diagnosis and awareness.
  50. Integrating optics, computer graphics and interactive techniques can address this worldwide problem.So, because NETRA and CATRA are portable, low-cost, and easy to build and use, we created an initiative called EyeNETRA.com to spread these hardware apps. We aim to increase the accessibility for eye care in remote parts of the world.These hardware apps will empower millions of people through patient centric ecosystems that start with diagnosis and awareness.
  51. Integrating optics, computer graphics and interactive techniques can address this worldwide problem.So, because NETRA and CATRA are portable, low-cost, and easy to build and use, we created an initiative called EyeNETRA.com to spread these hardware apps. We aim to increase the accessibility for eye care in remote parts of the world.These hardware apps will empower millions of people through patient centric ecosystems that start with diagnosis and awareness.
  52. The distant vision glasses in fact are sold for $3 and yet everyone makes profit.
  53. Integrating optics, computer graphics and interactive techniques can address this worldwide problem.So, because NETRA and CATRA are portable, low-cost, and easy to build and use, we created an initiative called EyeNETRA.com to spread these hardware apps. We aim to increase the accessibility for eye care in remote parts of the world.These hardware apps will empower millions of people through patient centric ecosystems that start with diagnosis and awareness.
  54. Integrating optics, computer graphics and interactive techniques can address this worldwide problem.So, because NETRA and CATRA are portable, low-cost, and easy to build and use, we created an initiative called EyeNETRA.com to spread these hardware apps. We aim to increase the accessibility for eye care in remote parts of the world.These hardware apps will empower millions of people through patient centric ecosystems that start with diagnosis and awareness.
  55. Not only bring those with blurry vision into the real world But in fact provide new jobs New micro-entreprenuer models (like grameen phone)These entreprenuer will technology to masses in scale and in unimaginable ways