Collectively, we take upwards of a trillion photos each year. These images together comprise a nearly complete visual record of the world's people, places, things, and events. However, this record is massively disorganized, unlabeled, and untapped. This talk explores ways of transforming this massive, unorganized photo collection into reconstructions and visualizations of the world's sites, cities, and people. After a brief recap of our work on Photosynth and reconstructing Rome in a day, I will present new work on modeling places and people from large photo collections from my research group at the University of Washington, and the product group that I direct at Google.

Steven Seitz is a Professor in the Department of Computer Science and Engineering at the University of Washington. He also directs a computer vision group at Google's Seattle office. 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 in 1997. Following his doctoral work, he spent one year visiting the Vision Technology Group at Microsoft Research and the subsequent 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 he has received an NSF Career Award, and ONR Young Investigator Award, and an Alfred P. Sloan Fellowship, and is an IEEE Fellow. His work on Photo Tourism (joint with Noah Snavely and Rick Szeliski) formed the basis of Microsoft's Photosynth technology. Professor Seitz is interested in problems in computer vision and computer graphics. His current research focuses on 3D modeling and visualization from large photo collections.