PhD Student
Department of Computer Science
University of North Carolina at Chapel Hill
Office: 364 Sitterson Hall
Email: rraguram at cs.unc.edu
Research
I'm interested in geometric problems in computer vision, such as large-scale structure-from-motion and robust estimation techniques. At UNC, I work with Jan-Michael Frahm and Marc Pollefeys. You can find more information (and videos!) describing our group's work in large-scale 3D reconstruction here. Be sure to try viewing the 3D models geo-referenced within Google Earth.
Prior to UNC, I was at the University of Arizona, where I obtained a Masters degree in Electrical and Computer Engineering, advised by Prof. Michael W. Marcellin. My thesis developed efficient techniques for bi-level image compression using JPEG2000. Here's a (very) high-level description via an invention disclosure.
At Arizona, I also worked on a few vision-related research projects with Kobus Barnard. I prototyped a multi-camera self-calibration system based on the work of Svoboda et al (link). Also, as part of a joint effort with Ravishankar Palanivelu, we developed some preliminary methods for quantitatively analysing images of microscopic biological structure (specifically, pollen-tube images captured with a fluorescence microscope). Here's a link that provides some motivation for this problem.
Publications
Journal
-
Improved Resolution Scalability for Bi-level Image Data in JPEG2000
[pdf]
Rahul Raguram, Michael W. Marcellin and Ali Bilgin.
IEEE Transactions on Image Processing, Vol. 18, No. 4, pp. 774-782, April 2009.
[Note: This is an extended version of our conference paper at DCC 2007]
Conference
-
Exploiting Uncertainty in Random Sample Consensus
[pdf]
Rahul Raguram, Jan-Michael Frahm and Marc Pollefeys.
International Conference on Computer Vision (ICCV), October 2009.
3D Reconstruction of Architectural Scenes From Uncalibrated Video Sequences [pdf]
Jan-Michael Frahm, Marc Pollefeys, Brian Clipp, David Gallup, Rahul Raguram, Changchang Wu, and Christopher Zach.
3D Virtual Reconstruction and Visualization of Complex Architectures (3D-ARCH), February 2009.
A Comparative Analysis of RANSAC Techniques Leading to Adaptive Real-Time Random Sample Consensus [pdf]
Rahul Raguram, Jan-Michael Frahm and Marc Pollefeys.
European Conference on Computer Vision (ECCV), October 2008.
Computing Iconic Summaries of General Visual Concepts [pdf]
Rahul Raguram and Svetlana Lazebnik.
Workshop on Internet Vision, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2008.
A Mobile 3D City Reconstruction System [pdf]
Brian Clipp, Rahul Raguram, Jan-Michael Frahm, Greg Welch, and Marc Pollefeys.
Workshop on Virtual Cityscapes, IEEE Virtual Reality, March 2008.
Improved Resolution Scalability for Bi-level Image Data in JPEG2000 [pdf]
Rahul Raguram, Michael W. Marcellin and Ali Bilgin.
IEEE Data Compression Conference (DCC), pp.203-212, Snowbird, Utah, March 2007.
Patents
-
Enhanced JPEG2000 Implementation for Bi-level
Image Processing [pdf]
Rahul Raguram, Michael W. Marcellin and Ali Bilgin.
Provisional Patent Application filed (University of Arizona, 2007).
Education
MS, Electrical and Computer Engineering, University of Arizona, Tucson
BE, Electronics and Communication Engineering, RVCE, Bangalore, India