| Class Times: | Wednesday 10:30am-12:30pm |
| Units: | 0-9-0 |
| Location: | E15-235 |
| Instructor: | Ramesh Raskar |
| raskar(at)media.mit. |
|
| Office Hours: | By appointment (Room #324) |
Course description
With more than a billion people with
networked,
mobile cameras in their hands, we are seeing a rapid evolution in
activities
based on visual exchange. People’s daily activities are increasingly
based on
pervasive recording and eager consumption of images and video. In this
seminar course,
we will look at the technical as well the social aspects of this
rapidly
evolving camera culture.
Current systems accomplish mid and high-level visual processing by
analyzing
images from ordinary cameras that have limited abilities. Can
innovative camera-like
sensors overcome the tough problems in scene understanding and generate
insightful awareness? Can new algorithms exploit, for example, unusual
optics,
programmable wavelength control or femto-second accurate photon
counting to
decompose the sensed values into perceptually critical elements? A
significant
enhancement in those cameras for scene analysis, and superior metadata
tagging
for effective sharing and display will bring about a revolution in
visual
communication. The new tools will spawn new visual art forms, optically
smart
sensors will empower disabled persons, pixel-coordinated interactions
will
harvest productivity of crowdsourcing for complex tasks and image-savvy
commerce will bring together cultures separated by language barriers.
We will explore novel hardware and software tools based on advanced
lenses,
digital illumination, modern sensors and emerging image-analysis
algorithms. The camera culture is transforming social interactions,
reshaping
businesses and
influencing communities worldwide. We will explore innovative protocols
for
sharing and consumption of visual media.
Format
The course will consist of lectures and guest talks followed by in-class discussion. The guest talks will be by the leaders in imaging industry.Prerequisites
Familiarity with imaging, camera techniques, applied optics and signal processing will be helpful.Grading
Each student will present one topic based on papers from the reading list and write one survey paper. To receive credit, you must attend regularly, present material on chosen topics and participate in discussions.
Schedule
Follow the link for each class to find a detailed description, suggested readings, and class slides. Some of the later classes may be subject to reordering or rescheduling.
Reading List
A list of suggested readings will be provided for each class.Computational Photography
- Siggraph
Course Notes, Raskar and Tumblin
- Computational
Photography: Mastering New Techniques for Lenses, Lighting, and Sensors
: 2008, A K Peters, Publishers
- Symposium on Computational Photography and Video Cambridge, MA (May 2005)
- Fredo Durand's list of useful
links and Computational
Photography course
More Links
What is Computational Camera, Shree Nayar http://www1.cs.columbia.edu/CAVE/projects/what_is/Great collection of projects, Shree Nayar http://www1.cs.columbia.edu/CAVE/projects/cc.php
Stanford Projects, Marc Levoy and collaborators http://graphics.stanford.edu/projects/lightfield/
Community Photo Collections at U of Washington http://grail.cs.washington.edu/projects/cpc/
CSAIL-MIT work on Computational Photography http://people.csail.mit.edu/fredo/photo.html
Jack Tumblin's 'Questions' for the field http://www.cs.northwestern.edu/~jet/research.html