prof.irfanessa.com » Frank Dellaert

Teaching: CS 4480 DVFX, Fall 08 “viral edition”

Irfan Essa — Tue, 19 Aug 2008 22:29:24 +0000

I am very pleased that my colleague (and friend) Professor Frank Dellaert has taken over my DVFX class that I have been teaching since 1999 (see site here). It is clear already that this new edition of the DVFX class will be even more exciting then the previous editions. Can’t wait to see the final videos. Check out the info on the class at CS 4480 DVFX, Fall 08.

Paper: ICCV (2003) “Spectral partitioning for structure from motion”

Irfan Essa — Mon, 13 Oct 2003 14:29:13 +0000

Steedly, D., Essa, I., Dellaert, F. (2003), “Spectral partitioning for structure from motion”, In Proceedings. Ninth IEEE International Conference on Computer Vision, 2003, 13-16 Oct. 2003, page(s): 996 – 1003 vol.2, Nice, France, ISBN: 0-7695-1950-4, INSPEC Accession Number:7971018, Digital Object Identifier: 10.1109/ICCV.2003.1238457, [IEEEXplore#]

Abstract

We propose a spectral partitioning approach for large-scale optimization problems, specifically structure from motion. In structure from motion, partitioning methods reduce the problem into smaller and better conditioned subproblems which can be efficiently optimized. Our partitioning method uses only the Hessian of the reprojection error and its eigenvector. We show that partitioned systems that preserve the eigenvectors corresponding to small eigenvalues result in lower residual error when optimized. We create partitions by clustering the entries of the eigenvectors of the Hessian corresponding to small eigenvalues. This is a more general technique than relying on domain knowledge and heuristics such as bottom-up structure from motion approaches. Simultaneously, it takes advantage of more information than generic matrix partitioning algorithms.

Project: DVFX@GeorgiaTech

Irfan Essa — Fri, 17 Sep 1999 13:20:38 +0000

DVFX@GeorgiaTech
The DVFX Group at the Georgia Tech’s GVU Center and the School of Interactive Computing is aimed at exploring the technical aspects of digital video special effects production and computer animation. For more information see the research at the Computational Perception Laboratory, and the class offerings in this area since 1999.

Check out the New BS in Computational Media, and the BS in Computer Science and its related specialization tracks (threads!) as options for degrees that include material described here.