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

Toward a Geometrically Coherent Image Interpretation

Alexei (Alyosha) Efros
April 10, 2006, 3:15PM (NOT 4:15PM)
(Room 200-205)


Image interpretation, the ability to see and understand the three-dimensional world behind a two-dimensional image, goes to the very heart of the computer vision problem. The ultimate objective is, given an image, to automatically produce a coherent interpretation of the depicted scene. This requires not only recognizing specific objects (e.g. people, houses, cars, trees), but understanding the underlying structure of the 3D scene where these objects reside.

In this talk I will describe some of our recent efforts toward this lofty goal. I will present an approach for estimating the coarse geometric properties of a scene by learning appearance-based models of geometric classes. Geometric classes describe the 3D orientation of image regions with respect to the camera. This geometric information is then combined with camera viewpoint estimation and local object detection producing a prototype for a coherent image-interpretation framework.

Joint work with Derek Hoiem and Martial Hebert at CMU.

About the Speaker

Alexei (Alyosha) Efros is originally from St. Petersburg, Russia, but, due to some mix-up at the travel agency, he now lives in Pittsburgh, USA. Alyosha got his PhD from UC Berkeley in 2003 under the direction of Jitendra Malik. He then spent a year as a Visiting Research Fellow in lovely Oxford, working with Andrew Zisserman and the Visual Geometry Group. Since 2004, he is an assistant professor at Carnegie Mellon University. Alyosha's research interests are in the area of computer vision and computer graphics, especially at the intersection of the two.


Back to the Colloquium Page