Varun Ganapathi

PhD Graduate
Computer Science Department
Stanford University
Stanford, CA 94305

About Me

I am a recent PhD graduate from the Computer Science department at Stanford University. I graduated with a MS CS and BS Physics in 2007 from Stanford University.

Research Interests

My recent interests lie in the intersection of probabilistic inference, machine learning and computer vision. I'm very excited by recent depth sensors that make it possible to capture full frames of color as well as range (RGBZ) measurements at 30fps (e.g., Microsoft Kinect). My own research centers around formulating new models for RGBZ data and using them to solve important perceptual problems such as tracking gestures, motion of joints, and activities.


Real Time Human Pose Tracking from Range Data Varun Ganapathi, Christian Plagemann, Daphne Koller and Sebastian Thrun ECCV 2012. [pdf]

Real Time Motion Capture Using a Single Time-Of-Flight Camera, Varun Ganapathi, Christian Plagemann, Daphne Koller and Sebastian Thrun CVPR 2010. [pdf]

Real Time Identification and Localization of Body Parts from Depth Images, Christian Plagemann, Varun Ganapathi, Daphne Koller and Sebastian Thrun ICRA 2010. [pdf]

Constrained Approximate Maximum Entropy Learning, Varun Ganapathi, David Vickrey, John Duchi and Daphne Koller UAI 2008. [pdf]

Efficient Structure Learning of Markov Networks using L1-Regularization, Su-In Lee, Varun Ganapathi and Daphne Koller NIPS 2006. [pdf]

Learning vehicular dynamics, with application to modeling helicopters, Pieter Abbeel, Varun Ganapathi and Andrew Y. Ng. NIPS 2005. [pdf]

Inverted autonomous helicopter flight via reinforcement learning, Andrew Y. Ng, Adam Coates, Mark Diel, Varun Ganapathi, Jamie Schulte, Ben Tse, Eric Berger and Eric Liang. In International Symposium on Experimental Robotics, 2004. [pdf]


Pro HDR is an app that I co-authored. Pro HDR allows you to automatically take high dynamic range (HDR) photos with a single tap. HDR is an interesting technique often used by professionals that can result in breathtaking photographs that can be qualitatively more similar to what the human eye sees.


Lua "is a powerful, fast, lightweight, embeddable scripting language." Use with luajit for best results.
SWIG makes it trivial to wrap C++ classes and use them from Lua.
Jennifer Widom's Tips for Writing Technical Papers

Class Papers

Simulation of Rigid Body Dynamics in Matlab
This report describes a MATLAB implementation of rigid body dynamics. Includes discussion of quaternions, Runge-Kutta order 4, and the inertia tensor.
[pdf], github


"It is not the critic who counts: not the man who points out how the strong man stumbles or where the doer of deeds could have done better. The credit belongs to the man who is actually in the arena, whose face is marred by dust and sweat and blood, who strives valiantly, who errs and comes up short again and again, because there is no effort without error or shortcoming, but who knows the great enthusiasms, the great devotions, who spends himself for a worthy cause; who, at the best, knows, in the end, the triumph of high achievement, and who, at the worst, if he fails, at least he fails while daring greatly, so that his place shall never be with those cold and timid souls who knew neither victory nor defeat"- Theodore Roosevelt

Google Scholar