Event Location: NSH 1305
Bio: Bryan Russell is a Research Scientist in the Creative Technologies Lab at Adobe Research in San Francisco. He received his Ph.D. from MIT in the Computer Science and Artificial Intelligence Laboratory in 2008 under the supervision of Professors William T. Freeman and Antonio Torralba. He was a post-doctoral fellow from 2008-2010 in the INRIA Willow team at the Département d’Informatique of Ecole Normale Supérieure in Paris, France. He was a research scientist with Intel Labs from 2012-2014 as part of the Intel Science and Technology Center for Visual Computing (ISTC-VC) and has been affiliated with the University of Washington since 2011.

Abstract: Much of our 3D visual world is depicted in text, maps, and images. In this talk I will describe work that reasons about such data, together with 3D geometry. In the first part I’ll describe an approach for analyzing text and annotated maps of a site, together with online photos, to produce annotated 3D models of famous tourist sites. The approach is completely automated, and leverages online text and photo co-occurrences. Our annotated models enable a number of user interactions, which we demonstrate in a novel 3D visualization tool. Text or map regions can be selected to move the camera to corresponding objects or rooms, 3D bounding boxes provide anchors back to text describing them, and the overall narrative of the text and map layout provide context for automatically flying through the scene. We show compelling results on several major tourist sites.