Internet-scale Scene Matching for Graphics and Vision
Friday, April 2, 2010
11:00 a.m. - 12:00 p.m.
Fuller Labs 320
Abstract:
The complexity of the visual world makes it difficult for computer vision
to understand images and for computer graphics to synthesize visual content.
The traditional computer graphics or computer vision pipeline mitigates this
complexity with a bottom up, divide and conquer strategy
(e.g. segmenting then classifying, assembling part-based models, or
using scanning window detectors).
In this talk I will discuss research that is fundamentally different, enabled
by the observation that while the space of images is infinite, the space of
"scenes" might not be astronomically large. With access to imagery
on an Internet scale, for most images there exist numerous semantically and
structurally similar scenes. My research is focused on exploiting and
refining large scale scene matching to short circuit the typical computer
graphics and vision pipelines for tasks such as
scene completion, image geolocation, and object detection.
______
James Hays is an assistant professor of computer
science at Brown University. Before joining Brown, James worked with Antonio
Torralba as a post-doc at Massachusetts Institute of Technology. He received
a Ph.D. in Computer Science from Carnegie Mellon University in 2009 while
working with Alexei Efros, and a B.S. in Computer Science from Georgia
Institute of Technology in 2003. His research interests are in computer
vision and computer graphics, focusing on image understanding and
manipulation leveraging massive amounts of data.
Host: Prof. Charles Rich
Refreshments
will be served.
|
