profile picture

Siddharth Choudhary

Computer Vision Researcher/Engineer
@ Magic Leap

Education

Ph.D. in Computer Science

Georgia Institute of Technology
2012 - 2017

MS in Computer Science

IIIT Hyderabad
2010 - 2012

BS in Computer Science

IIIT Hyderabad
2006 - 2010

Languages

  • Hindi (Native)
  • English (Professional)

Interests

  • Travelling
  • Kayaking
  • Running

About Me

I am a Computer Vision Researcher/Engineer (2017-) at Magic Leap. My primary research interests are in the areas of Robotics and Computer Vision and its intersection with Machine Learning and High Performance Computing.

Prior to that, I finished my Ph.D. (2012-2017) from the School of Interactive Computing, which is a part of College of Computing at Georgia Tech. I was associated with Cognitive Robotics and BORG lab and I was advised by Henrik I. Christensen and Frank Dellaert. I also collaborated with Luca Carlone, Vadim Indelman, Alex Trevor, Carlos Nieto, John Rogers and many others over the course of my PhD. I completed my Bachelors and Masters in Computer Science from IIIT Hyderabad in July 2012 working with P J Narayanan at CVIT.

I have also interned at Fyusion Inc. and spent some time collaborating with researchers from Army Research Lab which also has funded my research.

Experiences

Computer Vision Researcher/Engineer

2017 - Present
Magic Leap, Sunnyvale, CA

Graduate Research Assistant

2012 - 2017
Georgia Tech, Atlanta, GA

Research Intern

May 2016 - July 2016
Fyusion Inc, San Francisco, CA

Research Assistant

2010 - 2012
CVIT, IIIT-H, India

Google Summer of Code Scholar

May 2011 - Aug 2011
Point Cloud Library

Projects

Here are some of the projects for which I released or contributed to the source code

Distributed-Mapper - This library is an implementation of the algorithm described in Distributed Trajectory Estimation with Privacy and Communication Constraints: a Two-Stage Distributed Gauss-Seidel Approach (ICRA 2016, IJRR 2017). The core library is developed in C++ language.
ADMM-SLAM - This library is an implementation of the algorithm described in Exactly Sparse Memory Efficient SLAM using the Multi-Block Alternating Direction Method of Multipliers (IROS 2015). The core library is developed in C++ language.
Planning-to-Calibrate - This library is an implementation of the algorithm described in Active Planning Based Extrinsic Calibration of Exteroceptive Sensors in Unkown Environments (IROS 2016). The core library is developed in C++ and MATLAB
OmniMapper - A multi-modular mapping framework

Selected Publications

Siddharth Choudhary
Distributed Object based SLAM
Ph.D. Thesis [pdf] [ppt]
Titus Cieslewski, Siddharth Choudhary, Davide Scaramuzza
Data-Efficient Decentralized Visual SLAM
ICRA 2018 [pdf]
Siddharth Choudhary, Luca Carlone, Carlos Nieto, John Rogers, Henrik I. Christensen, Frank Dellaert
Distributed Mapping with Privacy and Communication Constraints:
Lightweight Algorithms and Object-based Models
IJRR 2017 [arxiv] [code] [bibtex]
Siddharth Choudhary, Luca Carlone, Carlos Nieto,
John Rogers, Zhen Liu, Henrik I. Christensen, Frank Dellaert
Multi Robot Object-based SLAM
ISER 2016 [pdf] [bibtex]
Siddharth Choudhary, Luca Carlone, Carlos Nieto, John Rogers, Henrik I. Christensen, Frank Dellaert
Distributed Trajectory Estimation with Privacy and Communication Constraints:
a Two-Stage Distributed Gauss-Seidel Approach
ICRA 2016 [pdf] [ppt] [www] [bibtex]
Siddharth Choudhary, Vadim Indelman, Henrik I. Christensen, Frank Dellaert
Information based Reduced Landmark SLAM
ICRA 2015 [pdf] [ppt] [bibtex]
Siddharth Choudhary and P J Narayanan
Visibility Probability Structure from SfM Datasets and Applications
ECCV 2012 [pdf] [www] [bibtex]

Check out ResearchGate or Google Scholar for complete list of publications.