Face to face - in realistic 3D

UK experts develop super-realistic animation system

Computing experts at Cardiff University, UK, are developing a super-realistic animation system that simulates the movements of a face, based on speech.
The team in the School of Computer Science has developed highly advanced software which is continually learning the facial dynamics associated with a speaker and applying this knowledge to synthesize realistic facial animations.

"Our aim is to create sophisticated facial animation through speech," explained Dr David Marshall. "The applications include a new sophistication in film, computer graphics and animation technology – not just for films and games, but also for educational, mobile telecommunications, advertising, information services and internet applications."

The team has now become the first to invest in the latest video camera technology from US company 3dMD. This latest generation "4D system" is the first commercially available product that combines the element of time with the rapid generation of medically accurate 3D surface models.

"We had exhausted the possibilities of 2D technology," said Dr Marshall. "The new camera enables us to capture high quality data at very high speed, and will provide the next level of detail to reproduce expressions and the subtle nuances that happen during speech."

Source: Cardiff University


Explore further

Alexa as your new bestie: Can an AI robot or voice assistant help you feel less lonely?

Citation: Face to face - in realistic 3D (2005, March 14) retrieved 13 November 2019 from https://phys.org/news/2005-03-realistic-3d.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.
0 shares

Feedback to editors

User comments