Tanner Schmidt

I am currently a Research Scientist at Facebook Reality Labs Research (FRLR). I am most interested in research with robotics and computer vision applications. In particular I enjoy working at the intersection of 3D geometry and modern machine learning techniques, where one can leverage both large amounts of data and principles of geometry that have been known for millennia.

Before FRLR, I did my Ph.D. in Computer Science and Engineering at the University of Washington. At UW, I was a member of the Robotics and State Estimation Lab advised by Dieter Fox. Prior to that, I did my bachelor’s in both Computer Science and Electrical and Computer Engineering at Duke University.

Publications:

• Model-Based Self-Supervision for Fine-Grained Image Understanding
  T. Schmidt
  Ph.D. Dissertation
  
  
  [pdf]
  Self-supervised Visual Descriptor Learning for Dense Correspondence
  T. Schmidt, R. A. Newcombe, D. Fox
  Robotics and Automation Letters
  - Best Robotic Vision Paper Award
  
  [pdf] | [vid]
• DART: Dense Articulated Real-Time Tracking with Consumer Depth Cameras
  T. Schmidt, R. A. Newcombe, D. Fox
  Autonomous Robots, Volume 39, Issue 3 (2015)
  
  
  [pdf] | [bib]
• Depth-Based Tracking with Physical Constraints for Robot Manipulation
  T. Schmidt, K. Hertkorn, R. A. Newcombe, Z. Marton, M. Suppa, D. Fox
  IEEE International Conference on Robotics and Automation (ICRA) 2015
  - Finalist, Best Robotic Vision Paper Award
  
  [pdf] | [vid]
• DART: Dense Articulated Real-Time Tracking
  T. Schmidt, R. A. Newcombe, D. Fox
  Robotics: Science and Systems (RSS) 2014
  
  [pdf] | [bib] | [vid]