Machine Learning-based Gaze Correction for Videoconferencing


Licensed exclusively in a field of use. For more information about IP rights still available for licensing outside of the field of use please contact us at .


Gaze correction, machine learning, predictor, decision forest


Videoconferencing and other remote video communication systems

Problem statement

The problem of gaze in videoconferencing has been attracting researchers and engineers for a long time. The problem manifests itself as the inability of the people engaged into a videoconferencing (the proverbial “Alice” and “Bob”) to maintain gaze contact. The lack of gaze contact is due to the disparity between Bob’s camera and the image of Alice’s face on Bob’s screen (and vice versa).


We revisit the problem of gaze correction and present a solution based on supervised machine learning. At training time, our system observes pairs of images, where each pair contains the face of the same person with a fixed angular difference in gaze direction. It then learns to synthesize the second image of a pair from the first one. After learning, the system becomes able to redirect the gaze of a previously unseen person by the same angular difference (10 or 15 degrees upwards in our experiments). Unlike many previous solutions to gaze problem in videoconferencing, ours is purely monocular, i.e. it does not require any hardware apart from an in-built web-camera of a laptop. Being based on efficient machine learning predictors such as decision forests, the system is fast (runs in real-time on a single core of a modern laptop).


  • High realism (no “stering” effect)
  • High resource effectiveness
  • Requires no extra hardware
  • No person-specific learning required, thus allowing to use the solution out-of-the-box.


  • Daniil Kononenko
  • Dr. Victor Lempitsky

Intellectual Property

  • Patent application: RU 1503007


  1. Daniil Kononenko, Victor Lempitsky / Learning To Look Up: Realtime Monocular Gaze Correction Using Machine Learning / IEEE Computer Vision and Pattern Recognition (CVPR), Boston MA, 2015

 Back to Skoltech technologies list >>

If you are interested in this technology please contact the KTO staff to discuss licensing opprotunities or R&D collaboration