I recently gave a talk at ICCP 2015 and clarified that we should stop working on coded aperture for focus effects! (Thus negating my team's work in this area.). I also spoke about the lost decade of computational photography and how we have wasted too many years working on the wrong problems.
4. Camera Phone
SLR-like
Super Human Vision
Friend:
Pixel Hacking
Past: Now: Future:
Immature Mature
Expectations
Burst Mode Tricks
Epsilon Photography
Delights
Drag:
Lost Decade of
Computational
Photography
5. Goal and Experience
Low Level Mid Level High
Level
Hyper
realism
Raw
Angle,
spectrum
aware
Non-visual
Data, GPS
Metadata
Priors
Capture
Process
Comprehensive
8D reflectance
field
Digital
Epsilon
Coded
Essence
CP aims to
make progress
on both axis
Camera Array
HDR, FoV Focal stack
Decompositio
n problems
Depth
Spectrum
LightFields
Human Stereo
Vision
Transient
Imaging
Virtual Object
Insertion
Relighting
Augmented
Human
Experience
Material
editing from
single photo
Scene
completion
from photos
Motion
Magnification
Phototourism
6. Future of Imaging
• What will a camera/display look like in 20 years?
• How will the next billion cameras change the social culture?
• How can we augment the camera to support best ‘image search’?
• How will portable health diagnostics impact healthcare?
• Will we live mostly in virtual/augmented reality, telepresent? TiVo for life?
• How will ultra-high-speed/resolution imaging change us?
• How can we improve ‘trust’ in imaging?
• Can we print anything .. Cars, food, .. babies .. (Amazon?)
• What are the opportunities in pervasive recording? e.g. GoogleEarth Live
• What will be in Photoshop2030?
• What is the future of movie-making, news reporting, sports viewing?
7. Camera of the Future
Cloth
Blimp/Drone
Flat-cam
Retinal
Implant
Disappear into
gadgets
27. Unbounded HDR using a Modulo Camera
Zhao, Shi, Fernandez-Cull, Sai-Kit Yeung, Raskar
ICCP 2015
28.
29. Visual Urban Sensing
Naik, Glaeser, Hidalgo, Raskar (email: naik@mit.edu)
Crowdsourcing
Computer Vision
+
3.6/10
Sentiment Analysis
for Street-level Images
Quantifying Urban Change
Applications: Real estate, Data-driven urban policy and planning
Decline
Improvement
streetscore.media.mit.edu
How to use computer vision
and crowdsourcing to
evaluate the appearance of
cities across the world
at street-level resolution and
global scale?
35. • Post-capture control
• Emulate studio lights with compact flash
• Focus and motion blur
• New forms
• Flat camera, large LCDs as cameras
• Shallow DoF with small aperture
• Understand the world
• Real or fake
• Place 2D photo into 3D
• Augmented Reality
• Sharing
• Lifelogs auto summary
• Privacy/Verification
• 6D photoframes
• Essence
• New visual arts
Computational Photography Wish List
S
e
n
s
o
r
36. Camera Phone
SLR-like
Super Human Vision
Friend:
Pixel Hacking
Past:
Photon Hacking
Now:
Physics Hacking
Experience Hacking
Future:
Emotion Hacking
Essence Hacking
Immature Mature
Expectations
Burst Mode Tricks
HyperData+ML
Delights
Lost Decade of
Computational
Photography
2008-2018
Glorious Decade of
Computational
Photography
2020’s
Drag:
Editor's Notes
http://en.wikipedia.org/wiki/Kano_model
http://en.wikipedia.org/wiki/Kano_model
http://en.wikipedia.org/wiki/Kano_model
Superman can fly and heroes can becomes invisible .. But what about a new power for a future super-hero ..
To see around corners ..
My idea is to use the multiple bounces of light i.e. echoes of light.
Echoes of sound -> Echoes of light
We all know about echoes of sound.
But sounds travels slow and we can actually hear the echoes
Light travels fast so we need specialized hardware to ‘listen’ to these echoes.
So we end up using light sources and cameras that run at a trillion frames per second (not a million and not a billion, but trillion)
Refl.mode THz TDS is actually ToF
Advantages: high time res.
Ideal case and its challenges
Reading through a closed
book
http://en.wikipedia.org/wiki/Kano_model
http://en.wikipedia.org/wiki/Kano_model
Ancient text witout damaging books
Provide oral health solutions via a tooth brush that takes achieves x-ray like screening
My work involves creative new ways to play with light by co-designing optical and digital processing.
My work lies at the INTERSECTION of processing of photons and processing of bits.
At MERL, I transformed the field of computational photography, with key papers and impact on products
At Media Lab, I invented a new field ‘computational light transport’