Seminars/Colloquia/Invited Talks

Seminars

Steve Seitz

Reconstructing Shape, Reflection, and Interreflection by Example

PLACE:	Clark 314
EVENT:	CIS Seminar Series
DATE:	March 07, 2006
TIME:	1:00 - 2:00

Abstract

Everyday objects and scenes reflect light in complex ways. For example, the reflection characteristics of wood, hair, or velvet vary substantially from one sample to the next and are very difficult to model analytically. Furthermore, scene appearance is affected by global scattering effects such as interreflections, shadows, and volumetric scattering. Modeling such effects is therefore of major practical importance in computer vision.
In this talk I argue for the use of "example-based" models of light transport; by controlling the illumination in the scene and measuring the reflected light, the captured images themselves provide a example of how light propagates through that specific scene. This model can be used to invert the light transport process directly in order to correctly recover shape, reflectance, or other scene properties, bypassing the need for complex simulations or optimizations of the underlying physical process. An additional advantage of these "example-based" techniques is that they work in very general conditions, significantly expanding the scope of the current state of the art.

Brief Biography

Steve Seitz is Short-Dooley Associate Professor in the Department of Computer Science and Engineering at the University of Washington. He received his B.A. in Computer Science and Mathematics at the University of California, Berkeley in 1991 and his Ph.D. in computer sciences at the University of Wisconsin, Madison in 1997. Following his doctoral work, he spent one year visiting the Vision Technology Group at Microsoft Research, and subsequently two years as an Assistant Professor in the Robotics Institute at Carnegie Mellon University. He joined the faculty at the University of Washington in July 2000. He was twice awarded the David Marr Prize for the best paper at the International Conference of Computer Vision, and has received an NSF Career Award, an ONR Young Investigator Award, and an Alfred P. Sloan Fellowship. His current research focuses on capturing the structure, appearance, and behavior of the real world from digital imagery.