Modelling Structures for Image-Based 3D Reconstruction - PhD Thesis Proposal

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F10%3A00175505" target="_blank" >RIV/68407700:21230/10:00175505 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Modelling Structures for Image-Based 3D Reconstruction - PhD Thesis Proposal

Popis výsledku v původním jazyce

This thesis proposal sets its place in a particular area of computer vision that deals with image based reconstruction of scenes exhibiting structure, but also aims at development of more general methods for stochastic model inference. Abstract In the first part the state of the art in the chosen area is given and analyzed, starting with unconstrained 3D reconstruction methods, followed by discussion on reconstruction methods exploiting both scene structure and understanding to obtain more accurate models enriched by details and semantics. Finally we focus on facade interpretation, which is chosen as a representative for a class of structural computer vision problems. Abstract Second part presents our recent research results, which demonstrate hands-onexperience with the mentioned topics that allows us to set ground for proposing next research interests and thesis objectives within described area. The stochastic Markov chain Monte Carlo framework is here chosen as the appropriate tool

Název v anglickém jazyce

Modelling Structures for Image-Based 3D Reconstruction - PhD Thesis Proposal

Popis výsledku anglicky

This thesis proposal sets its place in a particular area of computer vision that deals with image based reconstruction of scenes exhibiting structure, but also aims at development of more general methods for stochastic model inference. Abstract In the first part the state of the art in the chosen area is given and analyzed, starting with unconstrained 3D reconstruction methods, followed by discussion on reconstruction methods exploiting both scene structure and understanding to obtain more accurate models enriched by details and semantics. Finally we focus on facade interpretation, which is chosen as a representative for a class of structural computer vision problems. Abstract Second part presents our recent research results, which demonstrate hands-onexperience with the mentioned topics that allows us to set ground for proposing next research interests and thesis objectives within described area. The stochastic Markov chain Monte Carlo framework is here chosen as the appropriate tool

Druh

O - Ostatní výsledky

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2010

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů