Rahul Raguram

I’m a research manager at Apple, where I work on the 3D Vision Team. My team and I work on technology that powers features such as Visual Localization for Maps and Augmented Reality, detailed 3D city maps, Look Around, and 3D Flyover. We tackle a lot of fun (and challenging) problems in large scale 3D mapping, geometry and positioning using a mix of classical geometry and machine learning. If any of this sounds interesting, feel free to get in touch!

I ~~recently~~ a while ago received a PhD from the Department of Computer Science at UNC Chapel Hill. I worked in the 3D Computer Vision group, advised by Jan-Michael Frahm and Marc Pollefeys. During my PhD, I focused on applications that involved 3D 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.

news

Jun 7, 2021	AR Walking and detailed 3D city maps released with iOS 15.
Jun 22, 2020	Refine Location released in iOS 14, which uses visual localization to postion users accurately in the world. Also released as an API for 3rd party AR developers.

selected publications

ECCV

Building Rome on a Cloudless Day

Jan-Michael Frahm, Pierre Fite-Georgel, David Gallup, Tim Johnson, Rahul Raguram, Changchang Wu, Yi-Hung Jen, Enrique Dunn, Brian Clipp, Svetlana Lazebnik, and others

In European Conference on Computer Vision (ECCV) 2010

Bib PDF

@inproceedings{frahm2010building,
  title = {Building Rome on a Cloudless Day},
  author = {Frahm, Jan-Michael and Fite-Georgel, Pierre and Gallup, David and Johnson, Tim and Raguram, Rahul and Wu, Changchang and Jen, Yi-Hung and Dunn, Enrique and Clipp, Brian and Lazebnik, Svetlana and others},
  booktitle = {European Conference on Computer Vision (ECCV)},
  pages = {368--381},
  year = {2010},
  organization = {Springer, Berlin, Heidelberg},
}

Journal

Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs

Rahul Raguram, Changchang Wu, Jan-Michael Frahm, and Svetlana Lazebnik

International Journal of Computer Vision (IJCV) 2011

Bib PDF

@article{raguram2011modeling,
  title = {Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs},
  author = {Raguram, Rahul and Wu, Changchang and Frahm, Jan-Michael and Lazebnik, Svetlana},
  journal = {International Journal of Computer Vision (IJCV)},
  volume = {95},
  number = {3},
  pages = {213--239},
  year = {2011},
  publisher = {Springer US},
}

Journal

USAC: A universal framework for random sample consensus

Rahul Raguram, Ondrej Chum, Marc Pollefeys, Jiri Matas, and Jan-Michael Frahm

IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) 2012

Bib PDF

@article{raguram2012usac,
  title = {USAC: A universal framework for random sample consensus},
  author = {Raguram, Rahul and Chum, Ondrej and Pollefeys, Marc and Matas, Jiri and Frahm, Jan-Michael},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)},
  volume = {35},
  number = {8},
  pages = {2022--2038},
  year = {2012},
  publisher = {IEEE},
}

Journal

On the Privacy Risks of Virtual Keyboards: Automatic Reconstruction of Typed Input from Compromising Reflections

Rahul Raguram, Andrew M White, Yi Xu, Jan-Michael Frahm, Pierre Georgel, and Fabian Monrose

IEEE Transactions on Dependable and Secure Computing (TDSC) 2013

Bib PDF

@article{raguram2013privacy,
  title = {On the Privacy Risks of Virtual Keyboards: Automatic Reconstruction of Typed Input from Compromising Reflections},
  author = {Raguram, Rahul and White, Andrew M and Xu, Yi and Frahm, Jan-Michael and Georgel, Pierre and Monrose, Fabian},
  journal = {IEEE Transactions on Dependable and Secure Computing (TDSC)},
  volume = {10},
  number = {3},
  pages = {154--167},
  year = {2013},
  publisher = {IEEE},
}