Grant: Discovery Grants Program - Individual
University of Toronto
$39,000.00
Frontiers of three dimensional photography
EF 2007-08
Résumé
The long-term goal of this research is the automatic construction of geometric representations that accurately capture the three-dimensional shape and appearance of real, highly-complex scenes in the physical world---objects, indoor/outdoor environments, and people. Toward this end, the proposed work aims to push forward the state of the art in the field of "3D photography" by tackling, among others, two classes of everyday scenes for which no general (or practical) 3D photography methods exist: (1) objects made of transparent, refractive, or highly-reflective media, such as glass or metal, that cause complex light propagation; and (2) natural scenes with high geometric complexity, such as hair, fur and dense foliage.The scenes under investigation require new approaches to 3D photography and pose challenges both at a fundamental theoretical level (modeling image formation, solving inverse problems, establishing reconstructibility conditions) and at a practical level (efficient acquisition techniques, robust algorithms). To attack them, the PI will pursue two general directions recently developed within his research group: (1) design and analysis of Light-Path Triangulation algorithms for reconstructing specular scenes, and (2) design of high-resolution 3D photography algorithms that rely on control of a digital camera's focus and/or aperture.This research will establish a theoretical foundation and a computational framework for designing 3D computer vision algorithms able to operate in a wider range of scenes than is currently possible. Moreover, tools and insights gained through this work are likely to lead to applications that impact photography enthusiasts at large (e.g., producing high-quality photos by controlling the aperture of a single-lens reflex camera).
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
250388-2007
Name nom
Kutulakos, Kiriakos
Department département
Computer Science
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2007
Competition year année de concours
2007
Award amount
39000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
331
Committee name en
Computing and Information Sciences - B
Committee name fr
Informatique - B
Area of application code
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
Research subject code
2603
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Computer vision
Research subject fr
Vision artificielle
Partie
1
Nb partie
5
Application title
Frontiers of three dimensional photography
Keyword
NA
Application summary
The long-term goal of this research is the automatic construction of geometric representations that accurately capture the three-dimensional shape and appearance of real, highly-complex scenes in the physical world---objects, indoor/outdoor environments, and people. Toward this end, the proposed work aims to push forward the state of the art in the field of "3D photography" by tackling, among others, two classes of everyday scenes for which no general (or practical) 3D photography methods exist: (1) objects made of transparent, refractive, or highly-reflective media, such as glass or metal, that cause complex light propagation; and (2) natural scenes with high geometric complexity, such as hair, fur and dense foliage.The scenes under investigation require new approaches to 3D photography and pose challenges both at a fundamental theoretical level (modeling image formation, solving inverse problems, establishing reconstructibility conditions) and at a practical level (efficient acquisition techniques, robust algorithms). To attack them, the PI will pursue two general directions recently developed within his research group: (1) design and analysis of Light-Path Triangulation algorithms for reconstructing specular scenes, and (2) design of high-resolution 3D photography algorithms that rely on control of a digital camera's focus and/or aperture.This research will establish a theoretical foundation and a computational framework for designing 3D computer vision algorithms able to operate in a wider range of scenes than is currently possible. Moreover, tools and insights gained through this work are likely to lead to applications that impact photography enthusiasts at large (e.g., producing high-quality photos by controlling the aperture of a single-lens reflex camera).