In this thesis, we address the problem of 3D reconstruction from a sequence of calibrated street-level photographs with a simultaneous focus on scalability and the use of structure priors in Multi-View Stereo (MVS).While both aspects have been studied broadly, existing scalable MVS approaches do not handle well the ubiquitous structural regularities, yet simple, of man-made environments. On the other hand, structure-aware 3D reconstruction methods are slow and scale poorly with the size of the input sequences and/or may even require additional restrictive information. The goal of this thesis is to reconcile scalability and structure awareness within common MVS grounds using soft, generic priors which encourage : (i) piecewise planarity, (ii...
Despite advances in Photogrametry and Computer Vision, automatic scene reconstruction from photograp...
La représentation par maillages surfaciques de scènes urbaines est devenue un prérequis à de nombreu...
International audienceWe propose a multi-view stereo reconstruction algorithm which recovers urban s...
In this thesis, we address the problem of 3D reconstruction from a sequence of calibrated street-lev...
The main goal of this thesis is to develop innovative and practicaltools for the reconstruction of b...
International audienceAbstract:In this paper, we address the problem of Multi-View Stereo (MVS) reco...
In computer vision, the 3D structure estimation from 2D images remains a fundamental problem. One of...
International audienceThe recent widespread availability of urban imagery has lead to a growing dema...
International audienceWe present an original multi-view stereo reconstruction algorithm which allows...
International audienceWe describe an original method to reconstruct a 3D scene from a sequence of im...
Abstract. Recently, researchers working in the fields of computer graphics and computer vision have ...
Special issue for ACCV09International audienceThis article describes an original method to reconstru...
Geometric approximation of urban objects with compact and accurate representation is a challenging p...
The automatic reconstruction of a scene surface from images taken by a moving camera is still an act...
State-of-the-art Multi-View Stereo (MVS) algorithms de-liver dense depth maps or complex meshes with...
Despite advances in Photogrametry and Computer Vision, automatic scene reconstruction from photograp...
La représentation par maillages surfaciques de scènes urbaines est devenue un prérequis à de nombreu...
International audienceWe propose a multi-view stereo reconstruction algorithm which recovers urban s...
In this thesis, we address the problem of 3D reconstruction from a sequence of calibrated street-lev...
The main goal of this thesis is to develop innovative and practicaltools for the reconstruction of b...
International audienceAbstract:In this paper, we address the problem of Multi-View Stereo (MVS) reco...
In computer vision, the 3D structure estimation from 2D images remains a fundamental problem. One of...
International audienceThe recent widespread availability of urban imagery has lead to a growing dema...
International audienceWe present an original multi-view stereo reconstruction algorithm which allows...
International audienceWe describe an original method to reconstruct a 3D scene from a sequence of im...
Abstract. Recently, researchers working in the fields of computer graphics and computer vision have ...
Special issue for ACCV09International audienceThis article describes an original method to reconstru...
Geometric approximation of urban objects with compact and accurate representation is a challenging p...
The automatic reconstruction of a scene surface from images taken by a moving camera is still an act...
State-of-the-art Multi-View Stereo (MVS) algorithms de-liver dense depth maps or complex meshes with...
Despite advances in Photogrametry and Computer Vision, automatic scene reconstruction from photograp...
La représentation par maillages surfaciques de scènes urbaines est devenue un prérequis à de nombreu...
International audienceWe propose a multi-view stereo reconstruction algorithm which recovers urban s...