Keynote: Jan-Michael Frahm, UNC Chapel Hill, USA - http://www.cs.unc.edu/~jmf

The status and future of (semi-)automatic image based reconstruction

Abstract: With the recent availability of large collections of images and videos through websites like Flickr and You Tube researchers have started to use the data for 3D reconstruction. There have been very successful approaches for both kinds of data that lead to powerful image based visualizations or real-time large scale modeling. While these approaches demonstrate impressive performance they are only the first steps on the way of fully deploying those data sources. The talk will review the current state of the art in the field of 3D reconstruction/modeling from image sequences/web photo collection and discuss some of the future challenges in this area.

Keynote: Ioannis Stamos, City University of New York, USA - http://www.cs.hunter.cuny.edu/~ioannis

Challenges in automated 3D modeling of urban environments

Abstract: The automated photorealistic modeling of large-scale scenes, such as urban structures, requires a fusion of range sensing technology and traditional digital photography. This process involves the automated registration and fusion of a large number of geometrically complex 3D range scans and high-resolution 2D images in a common frame of reference, and finally 3D modeling and data simplification. We will provide an overview of the challenges, and discuss our specific contributions. We will also present results of scanning large urban structures, such as the interior of the Grand Central Terminal in New York.