PhD Student
Department of Computer Science
University of North Carolina at Chapel Hill

Office: 362 Sitterson Hall
Email: rraguram at cs.unc.edu

 


About Me


I'm a software engineer/scientist at Apple, where I work on 3D maps. I recently finished my PhD in the Department of Computer Science at the University of North Carolina at Chapel Hill. I worked in the 3D Computer Vision group, advised by Jan-Michael Frahm and Marc Pollefeys. I enjoy working on various problems in computer vision and machine learning, and my recent research has focused on applications that involve the modeling and understanding of real-world scenes, objects and events.

Prior to UNC, I obtained a Masters degree in Electrial and Computer Engineering from the University of Arizona, where I was a member of the Signal Processing and Coding Lab.


Research Interests


The focus of my dissertation research is on developing efficient algorithms for robust estimation, particularly as applied to large-scale structure from motion problems. In particular, I've proposed algorithms for real-time robust estimation (ARRSAC), techniques for modeling the effects of noise and uncertainty in RANSAC (cov-RANSAC), as well as a framework for threshold-free robust estimation (RECON).

In addition to this, I've also worked on systems for:

  • Modeling and organization of large-scale internet photo collections (link)
  • Real-time 3D reconstuction from video (link)
  • Automated surveillance from compromising reflections (link)
  • Semantic scene understanding using a combination of imagery and 3D LIDAR geometry (link)
  • Efficient techniques for bi-level image compression using JPEG2000 (link)

Click here for a more detailed description of the above projects.


Publications


Journal
    On the Privacy Risks of Virtual Keyboards: Automatic Reconstruction of Typed Input from Compromising Reflections [pdf] [webpage] [slides]
    Rahul Raguram, Andrew White, Yi Xu, Jan-Michael Frahm, Pierre Georgel, and Fabian Monrose.

    IEEE Transactions on Dependable and Secure Computing, May-June 2013.


    USAC: A Universal Framework for Random Sample Consensus [pdf] [webpage]
    Rahul Raguram, Ondrej Chum, Marc Pollefeys, Jirı Matas , and Jan-Michael Frahm.

    IEEE Transactions on Pattern Analysis and Machine Intelligence, Nov 2012.


    Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs [pdf] [webpage]
    Rahul Raguram, Changchang Wu, Jan-Michael Frahm, and Svetlana Lazebnik.

    International Journal of Computer Vision, April 2011.


    Fast Robust Large-scale Mapping from Video and Internet Photo Collections [pdf]
    Jan-Michael Frahm, Marc Pollefeys, Svetlana Lazebnik, Christopher Zach, David Gallup, Brian Clipp, Rahul Raguram, Changchang Wu, Tim Johnson.

    Special issue: "100 years of ISPRS", ISPRS Journal of Photogrammetry and Remote Sensing, 2010.


    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
    Improved Geometric Verification for Large Scale Landmark Image Collections
    Rahul Raguram, Joseph Tighe, and Jan-Michael Frahm.

    British Machine Vision Conference (BMVC), 2012.


    Efficient and Scalable Depthmap Fusion
    Enliang Zheng, Enrique Dunn, Rahul Raguram, and Jan-Michael Frahm.

    British Machine Vision Conference (BMVC), 2012..


    RECON: Scale-Adaptive Robust Estimation via Residual Consensus [pdf] [code]
    Rahul Raguram and Jan-Michael Frahm.

    International Conference on Computer Vision (ICCV), 2011.


    iSpy: Automatic Reconstruction of Typed Input from Compromising Reflections [pdf] [webpage] [slides]
    Rahul Raguram, Andrew White, Dibyendusekhar Goswami, Fabian Monrose and Jan-Michael Frahm.

    ACM Conference on Computer and Communications Security (CCS), Oct 2011.


    Efficient Generation of Multi-Perspective Panoramas [pdf]
    Enliang Zheng, Rahul Raguram, Pierre Georgel and Jan-Michael Frahm.

    3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT), May 2011.


    Fast Organization of Large Photo Collections using CUDA [pdf]
    Tim Johnson, Pierre Georgel, Rahul Raguram and Jan-Michael Frahm.

    Workshop on Computer Vision on GPUs, European Conference on Computer Vision (ECCV), September 2010.


    Building Rome on a Cloudless Day [pdf]
    Jan-Michael Frahm, Pierre Georgel, David Gallup, Tim Johnson, Rahul Raguram, Changchang Wu, Yi-Hung Jen, Enrique Dunn, Brian Clipp, Svetlana Lazebnik, Marc Pollefeys.

    European Conference on Computer Vision (ECCV), September 2010.


    Fast Robust Reconstruction of Large Scale Environments [pdf]
    Jan-Michael Frahm, Marc Pollefeys, Svetlana Lazebnik, Brian Clipp, David Gallup, Rahul Raguram and Changchang Wu.

    Conference on Information Sciences and Systems (CISS), March 2010.


    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.

Tech Reports/Patents
    Large-scale 3D reconstruction from aerial video
    Rahul Raguram, Alexei N. Skurikhin and Jan-Michael Frahm.

    Los Alamos National Labs Technical Report, LA-UR-10-03842 (LANL, June 2010).


    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).

 

 

Last updated: Jan 2012