Srinath Sridhar

Srinath Sridhar
S297 Clark Center, 318 Campus Drive, Stanford, CA 94305
Srinath Sridhar I am a postdoctoral researcher at Stanford University working with Leonidas Guibas in the Geometric Computing Group. My research interests lie primarily in computer vision with broad applications in human–computer interaction and robotics.

The goal of my research is to digitize human physical interactions and manual skills from visual data so we can build more immersive virtual/augmented realities, and smarter robots. I develop methods that provide 3D human-centric, object-centric, and interaction-centric understanding of our world from videos and images. Please see the research tab for more details.

I obtained my PhD at the Max Planck Institute for Informatics in 2016 where I was advised by Christian Theobalt and Antti Oulasvirta. In my PhD thesis, I investigated key computer vision and interaction problems in gesture-based computer input. In the past, I have spent time at Microsoft Research Redmond (with Shahram Izadi), at the University of Michigan, Ann Arbor (working with Vineet Kamat), at the Honda Research Institute (with Victor Ng-Thow-Hing), and at the College of Engineering Guindy, Anna University.

CV  /  Google Scholar  /  Semantic Scholar  /  Github  /  Twitter


Google Scholar   /    Semantic Scholar


Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation
He Wang, Srinath Sridhar, Jingwei Huang, Julien Valentin, Shuran Song, Leonidas J. Guibas. Computer Vision and Pattern Recognition (CVPR) 2019 (Oral).
PDF  /  Video  /  Project Page
Learning Generalizable Physical Dynamics of 3D Rigid Objects
Davis Rempe, Srinath Sridhar, He Wang, Leonidas J. Guibas. arXiv preprint, arXiv:1901.00466, 2019.

Learning a Generative Model for Multi-Step Human-Object Interactions from Videos
He Wang*, Soeren Pirk*, Ersin Yumer, Vladimir Kim, Ozan Sener, Srinath Sridhar, Leonidas J. Guibas. Eurographics 2019. (* joint first authors)
PDF  /  Video  /  Project Page
Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB
Dushyant Mehta, Oleksandr Sotnychenko, Franziska Mueller, Weipeng Xu, Srinath Sridhar, Gerard Pons-Moll, Christian Theobalt. International Conference on 3D Vision (3DV) 2018.
PDF  /  Video  /  Project Page
GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB
Franziska Mueller, Florian Bernard, Oleksandr Sotnychenko, Dushyant Mehta, Srinath Sridhar, Dan Casas, Christian Theobalt. Computer Vision and Pattern Recognition (CVPR) 2018 (spotlight).
PDF  /  Video  /  Project Page
Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor
Franziska Mueller, Dushyant Mehta, Oleksandr Sotnychenko, Srinath Sridhar, Dan Casas, Christian Theobalt
International Conference on Computer Vision (ICCV) 2017.
PDF  /  Video  /  Project Page
VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
Dushyant Mehta, Srinath Sridhar, Oleksandr Sotnychenko, Helge Rhodin, Mohammad Shafiei, Hans-Peter Seidel, Weipeng Xu, Dan Casas, Christian Theobalt. ACM Transactions on Graphics (SIGGRAPH) 2017.
PDF  /  Video  /  Project Page
WatchSense: On- and Above-Skin Input Sensing through a Wearable Depth Sensor
Srinath Sridhar, Anders Markussen, Antti Oulasvirta, Christian Theobalt, Sebastian Boring
SIGCHI Conference on Human Factors in Computing Systems (CHI) 2017.
PDF  /  Video  /  Project Page
Tracking Hands in Action for Gesture-based Computer Input
Srinath Sridhar
Ph.D. Dissertation, Saarland University, 2016.
Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input
Srinath Sridhar, Franziska Mueller, Michael Zollhöfer, Dan Casas, Antti Oulasvirta, Christian Theobalt
European Conference on Computer Vision (ECCV) 2016.
PDF  /  Video  /  Project Page  / BibTeX
Fast and Robust Hand Tracking Using Detection-Guided Optimization
Srinath Sridhar, Franziska Mueller, Antti Oulasvirta, Christian Theobalt
Computer Vision and Pattern Recognition (CVPR) 2015.
PDF  /  Video  /  Project Page  /  BibTeX
Investigating the Dexterity of Multi-Finger Input for Mid-Air Text Entry
Srinath Sridhar, Anna Maria Feit, Christian Theobalt, Antti Oulasvirta
SIGCHI Conference on Human Factors in Computing Systems (CHI) 2015.
PDF  /  Video Summary  /  Project Page
Real-time Hand Tracking Using a Sum of Anisotropic Gaussians Model
Srinath Sridhar, Helge Rhodin, Hans-Peter Seidel, Antti Oulasvirta, Christian Theobalt
International Conference on 3D Vision (3DV) 2014. (Oral)
PDF  /  Video  /  Project Page  /  BibTeX
Interactive Markerless Articulated Hand Motion Tracking using RGB and Depth Data
Srinath Sridhar, Antti Oulasvirta, Christian Theobalt
International Conference on Computer Vision (ICCV) 2013.
PDF  /  Video  /  Project Page  /  BibTeX
User-Centered Perspectives for Automotive Augmented Reality
Victor Ng-Thow-Hing, Karlin Bark, Lee Beckwith, Cuong Tran, Rishabh Bhandari, Srinath Sridhar
International Symposium on on Mixed and Augmented Reality (ISMAR) 2013.
PDF  /  IEEE Xplore  /  BibTeX


HandSonor: A Customizable Vision-based Control Interface for Musical Expression
Srinath Sridhar
Extended Abstracts, SIGCHI Conference on Human Factors in Computing Systems (CHI) 2013.
PDF  /  Project Page  /  BibTeX
Generation of Virtual Display Surfaces for In-vehicle Contextual Augmented Reality
Srinath Sridhar, Victor Ng-Thow-Hing
International Symposium on on Mixed and Augmented Reality (ISMAR) 2012.
PDF  /  BibTeX


Method to Generate Virtual Display Surfaces from Video Imagery of Road based Scenery
Victor Ng-Thow-Hing, Srinath Sridhar
U.S. Patent, US 9135754 B2, 2015.
Google Patents

Technical Reports

FullHand: Markerless Skeleton-based Tracking for Free-Hand Interaction
Srinath Sridhar, Gilles Bailly, Elias Heydrich, Antti Oulasvirta, Christian Theobalt
MPI-I-2016-4-002. Saarbrücken: Max-Planck-Institut für Informatik 2016.
PDF  /  Pubman
Fast Tracking of Hand and Finger Articulations Using a Single Depth Camera
Srinath Sridhar, Antti Oulasvirta, Christian Theobalt
MPI-I-2014-4-002. Saarbrücken: Max-Planck-Institut für Informatik 2014.
PDF  /  Pubman
CAMFPLAN: A Real-time Markerless Camera Pose Estimation System for Augmented Reality
Srinath Sridhar, Vineet R. Kamat
UMCEE Report No. 11-01, Department of Civil and Environmental Engineering, University of Michigan, Ann Arbor 2012.



  • GRANSAC: A generic, multi-threaded, header-only RANSAC implementation for C++.
  • Kaadugal: A multi-threaded C++ implementation of the random forests algorithm for classification, regression, and structured prediction problems.