Grant: Engage Grants Program
Ryerson University
$16,916.00
Advanced 2D to 3D video conversion techniques
FY 2010-11
Summary
With both broadcast and recorded formats standardized, the film and television industry have embraced the
delivery of stereoscopic 3D content. As indicated by the recent success of several Hollywood films, there is
also a demand for 3D content at the consumer level. However, it will be several years before all content is shot
in 3D, as there is a large infrastructure built around pre-existing 2D technology. Thus, there is a window of
opportunity for a semi- or fully-automated process for converting 2D material to 3D. Additionally, there is a
large existing base of 2D material, both film and television, which could be resold if converted to 3D.
A principal aspect of converting 2D video to 3D is recovering a depth map for each frame. While the human
visual system is capable of inferring depth from 2D imagery, the process is not well understood and difficult to
replicate. We propose to research methods to develop a system ultimately based on multiple depth cues that is
able to recover relative depth to aid in the 2D to 3D conversion process.
Program
Engage Grants Program
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
401394-2010
Name nom
Androutsos, Dimitrious
Department département
Electrical and Computer Engineering
Organization id
43
Institution établissement
Ryerson University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2010
Competition year année de concours
2010
Award amount
16916
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1553
Committee name en
Ontario Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Ontario
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
2708
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Image processing
Research subject fr
Traitement des images
Partie
1
Nb partie
1
Application title
Advanced 2D to 3D video conversion techniques
Keyword
NSERC
Application summary
With both broadcast and recorded formats standardized, the film and television industry have embraced the
delivery of stereoscopic 3D content. As indicated by the recent success of several Hollywood films, there is
also a demand for 3D content at the consumer level. However, it will be several years before all content is shot
in 3D, as there is a large infrastructure built around pre-existing 2D technology. Thus, there is a window of
opportunity for a semi- or fully-automated process for converting 2D material to 3D. Additionally, there is a
large existing base of 2D material, both film and television, which could be resold if converted to 3D.
A principal aspect of converting 2D video to 3D is recovering a depth map for each frame. While the human
visual system is capable of inferring depth from 2D imagery, the process is not well understood and difficult to
replicate. We propose to research methods to develop a system ultimately based on multiple depth cues that is
able to recover relative depth to aid in the 2D to 3D conversion process.