Search this site
Search this site
Home
GoW Home
Back
Research Areas
Topic
Sector
Scheme
Region
Theme
Organisation
Partners
Details of Grant
EPSRC Reference:
GR/S27962/01
Title:
Video-Based Representation of Dynamic Scenes for Broadcast Content Production
Principal Investigator:
Hilton, Professor A
Other Investigators:
Researcher Co-Investigators:
Project Partners:
Avatarme Ltd
BBC
Sony (UK)
Department:
Sch of Electronics & Physical Sciences
Organisation:
University of Surrey
Scheme:
Standard Research (Pre-FEC)
Starts:
15 April 2004
Ends:
14 April 2007
Value (£):
267,985
EPSRC Research Topic Classifications:
Image & Vision Computing
Multimedia
EPSRC Industrial Sector Classifications:
Creative Industries
Information Technologies
Related Grants:
Panel History:
Panel Date
Panel Name
Outcome
04 Feb 2003
People & Interactivity Panel (Technology) - Feb 03
Deferred
Summary on Grant Application Form
Ilmage-based representations of static scenes derived from captured images have achieved 'photo-realistic' synthesis of novel views.The goal of this prc is to establish an equivalent 'video-based' representation for dynamic real-world scenes derived from multiple view video image sequences.This researct motivated by the demands of the entertainment industry for new technologies to provide greater flexibility in content production and manipulation while maintaining visual quality. Research will address three major challenges to enable flexible content production: user control over viewpoint, scene illumina and scene dynamics. The primary criteria for developing video-based representations of dynamic scenes is that synthesised image sequences should hi same 'video-realistic' visual quality as the captured image sequences. Research will be applied to the problem of representing moving people, which forr central element of most entertainment content. Video-realistic representation of people presents a challenging problem due to their high-dimensional nor structure including fine detail such as hair and clothing. Research will investigate novel video-based representations for parameterisation of complex SCE dynamics to allow user control, together with photo-metric representation of surface properties for dynamic scenes to support changes in illumination. Ultimately video-based representation with user control will enable video-realistic content production using techniques analogous to conventional 3D cha animation.
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Summary
Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:
Further Information:
Organisation Website:
http://www.surrey.ac.uk