Multi-view Reconstruction and Texturing - Archive ouverte HAL Access content directly
Theses Year : 2009

Multi-view Reconstruction and Texturing

Reconstruction multi-vues et texturation

(1, 2, 3)
1
2
3

Abstract

In this thesis, we study the problem of static and dynamic multiview reconstruction and texturing, particularly focusing on real applications. First, we propose three reconstruction methods sharing the objective of estimating a representation of a static/dynamic scene from a set of multiple images/videos. Then, we consider the problem of multi-view texturing, focusing on the visual correctness of the rendering. The contributions of this thesis are as follows : 1. A shape from silhouette approach is proposed producing a compact and high- quality 4D representation of the visual hull, o ering easy and extensive control over the size and quality of the output mesh as well as over its associated reprejection error. 2. A dynamic multi-view reconstruction method is proposed computing a 4D representation of a dynamic scene, based on a global optimization of a true spatio-temporal energy, taking visibility into account. 3. A photo-consistent surface reconstruction method is proposed incorporating the input images for better accuracy and robustness. 4. A multi-view texturing method is proposed computing a visually correct tex- turing of an imprecise mesh.
Dans cette thèse, nous étudions les problèmes de reconstruction statique et dynamique à partir de vues multiples et texturation, en s'appuyant sur des applications réelles et pratiques. Nous proposons trois méthodes de reconstruction destinées à l'estimation d'une représentation d'une scène statique/dynamique à partir d'un ensemble d'images/vidéos. Nous considérons ensuite le problème de texturation multi-vues en se concentrant sur la qualité visuelle de rendu..
Fichier principal
Vignette du fichier
Thesis_Aganj.pdf (12.18 Mo) Télécharger le fichier
Loading...

Dates and versions

pastel-00517742 , version 1 (15-09-2010)

Identifiers

  • HAL Id : pastel-00517742 , version 1

Cite

Ehsan Aganj. Multi-view Reconstruction and Texturing. Computer Vision and Pattern Recognition [cs.CV]. Ecole des Ponts ParisTech, 2009. English. ⟨NNT : 2009ENPC0918⟩. ⟨pastel-00517742⟩
275 View
379 Download

Share

Gmail Facebook Twitter LinkedIn More