Shuda Yu

Learn More
The automatic surface reconstruction from an image sequence is still an active research topic. Recently, a method was designed to reconstruct a 2-manifold surface from the sparse cloud of points generated by Structure-from-Motion (SfM). This method reconstructs outdoor scenes from hundreds of catadioptric images. It is based on sculpting the 3d Delaunay(More)
The majority of methods for the automatic surface reconstruction of an environment from an image sequence have two steps: Structure-from-Motion and dense stereo. From the computational standpoint, it would be interesting to avoid dense stereo and to generate a surface directly from the sparse cloud of 3D points and their visibility information provided by(More)
Automatic image-based-modeling usually has two steps: Structure from Motion (SfM) and the estimation of a trian-gulated surface. The former provides camera poses and a sparse point cloud. The latter usually involves dense stereo. From the computational standpoint, it would be nice to avoid dense stereo and estimate the surface from the sparse cloud(More)
La majorité des méthodes automatiques de modélisation 3d à partir d'images reconstruisent un ensemble dense de points. Nous proposons ici de reconstruire une surface di-rectement à partir de l'ensemble épars de points recons-truits en estimant la géométrie. Deux méthodes voisines sont présentées, l'une est progressive (la surface est pro-gressivement(More)
Modélisation 3d automatique d'environnements: une approché eparsè a partir d'images prises par une caméra catadioptrique Automatic 3d modeling of environments: a sparse approach from images taken by a catadioptric camera Soutenue publiquement le 3 juin 2013 devant le jury: and Thierry Chateau who agreed to be part of my thesis committee and take time to(More)
  • 1