Broad Area Colloquium For AI-Geometry-Graphics-Robotics-Vision
(CS 528)

Capturing Shape and Reflection from Images

Steve Seitz
Computer Science Department
University of Washington
Monday, March 1, 2004, 4:15PM
TCSeq 200


Surfaces in the real world reflect light in interesting and complex ways. For instance, wood looks the way it does (different from leather, skin, hair, satin, etc.) because it reflects light in a characteristic way, as a function of illumination, viewpoint, and surface-varying grain. While humans have no problem interpreting images of scenes with widely varying material properties, developing computational mechanisms for handling realistic materials is a wide open problem in computer vision.

In this talk, I will address the problem of reconstructing 3D shape models of scenes with very general reflectance properties from images. The resulting algorithms operate on an extremely broad class of materials and objects, ranging from wood, to oxidized metal, to brushed fur.

This is collaborative work with Dan Goldman, Adrien Treuille, Brian Curless, and Aaron Hertzmann.

About the Speaker

Steve Seitz is an 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 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 Fellowshp.


Back to the Colloquium Page