Video Games Help Teach Computer Vision Systems about the World

In recent years, deep learning has revolutionized how computer vision systems are developed, and made them more capable than ever before. These system work by learning from examples; in particular they require many real-world images that have been manually annotated to label the objects of interest. However the collection and annotation of these training images is
a slow and laborious process. An open question is whether computer graphics can by used as a convenient alternative method that directly generates as many annotated images as required for the learning. If the rendered training images are not sufficiently realistic, then the vision system will not do well on real images.

In research with his PhD supervisors, Jim Little and Mark Schmidt, Alireza Shafaei has found that training on images from the game performed just as well, and in some cases better than, training on available sets of real photos.  These results suggest that large-scale datasets from video games can be used to help better train vision systems for self-driving cars, sports analysis, and any other visual domain where it would otherwise be difficult to obtain large sets of labeled images.

This work has also been picked up already by MIT Technology Review
and others:

Site Categories Research

Department News

January 16, 2018
An investment from the Province of British Columbia will create 624 undergraduate spaces for...
January 10, 2018
CS Professor Kevin Leyton-Brown's team at the Federal Communications Commission is among the six...
January 5, 2018
Congratulations to Computer Science Professor Kevin Leyton-Brown, who has been named AAAI Fellow....
January 5, 2018
Artificial Intelligence (AI) is emerging as a disruptive technology. UBC researchers have long been...

a place of mind, The University of British Columbia


ICICS/CS Building 201-2366 Main Mall
Vancouver, B.C. V6T 1Z4 Canada
Tel: 604-822-3061 | Fax: 604-822-5485
Undergrad program:
Graduate program:

Emergency Procedures | Accessibility | Contact UBC | © Copyright The University of British Columbia