Ramin Zabih

Assistant Professor
Ph.D. Stanford University, 1994

My work in the field of computer vision covers both basic research issues and a range of new applications. My research group has developed a new approach to a variety of problems in early vision, based on the use of discrete optimization techniques. In joint work with

Yuri Boykov and Olga Veksler, we developed optimization algorithms based on graph cuts that can efficiently minimize a wide range of energy functions that arise in early vision. These methods rapidly produce answers with strong guarantees, and give excellent results for stereo and motion in practice. Working with Vera Kettnaker, we formulated the problem of tracking moving objects from multiple cameras in a Bayesian framework and solved it using a variant of linear programming. In recent work with Vladimir Kolmogorov, and with Daniel Snow and Paul Viola of MIT, we have developed techniques for solving recovering object shape from multiple cameras using graph cuts.

I am also exploring a number of different applications of computer vision. I have worked extensively with Microsoft over the last four years on automating some visual tasks that occur in the development of programs with graphical user interfaces.

Professional Activities

Chair: IEEE Workshop on Graph Algorithms and Computer Vision, 1999.

Program Committee Member: IEEE Conference on Computer Vision and Pattern Recognition, 2000.

Guest Editor: Special Issue of IEEE Transactions on Pattern Analysis and Machine Intelligence on Graph Algorithms and Computer Vision, 2000.


Energy minimization for computer vision via graph cuts. Microsoft Research, July 1999.

—. Xerox PARC, Palo Alto, CA, August 1999.

—. University of Toronto, Toronto, Ontario, October 1999.

—. MIT Artificial Intelligence Laboratory, Cambridge, MA, October 1999.

—. University of California at Berkeley, Berkeley, CA, October 1999.

—. Sarnoff Research, November 1999.

—. Columbia University, New York, NY, December 1999.


“Color-spatial indexing and applications.” International Journal of Computer Vision, vol. 35, no. 3 (1999), 245–268 (with J. Huang, S.R. Kumar, M. Mitra, and W. Zhu).

“Bayesian Multi-camera Surveillance.” IEEE Computer Vision and Pattern Recognition Conference (June 1999), 253–259 (with V. Kettnaker).

“Counting People from Multiple Cameras.” IEEE Conference on Multimedia Computing and Systems, Florence, Italy (June 1999), 267–271 (with V. Kettnaker).

“A New Algorithm for Energy Minimization with Discontinuities.” International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (July 1999), 205–220 (with Y. Boykov and O. Veksler).

“Fast Approximate Energy Minimization via Graph Cuts.” International Conference on Computer Vision (September 1999), 377–384 (with Y. Boykov and O. Veksler).

“An Experimental Comparison of Stereo Algorithms.” IEEE Workshop on Vision Algorithms. (September 1999) (with R. Szeliski).