Page principale | Projets | Publications | Thèses | Présentations | Membres | Cours | Gallerie | Intérêt local Home | Projects | Publications | Theses | Presentations | People | Courses | Gallery | Local interest

Abstract

We describe an interactive system to reconstruct 3D geometry and extract textures from a set of photographs taken with arbitrary camera parameters. The basic idea is to let the user draw 2D geometry on the images and set constraints using these drawings. Because the input comes directly from the user, he can more easily resolve most of the ambiguities and difficulties traditional computer vision algorithms must deal with.

A set of geometrical linear constraints formulated as a weighted least-squares problem is efficiently solved for the camera parameters, and then for the 3D geometry. Iterations between these two steps lead to improvements on both results. Once a satisfying 3D model is reconstructed, its color textures are extracted by sampling the projected texels in the corresponding images. All the textures associated with a polygon are then fitted to one another, and the corresponding colors are combined according to a set of criteria in order to form a unique texture.

The system produces 3D models and environments more suitable for realistic image synthesis and computer augmented reality.

BibTeX entry

@InProceedings{Poulin:1998:IMP,
  author =       "Pierre Poulin and Mathieu Ouimet and Marie-Claude Frasson",
  title =        "Interactively Modeling with Photogrammetry",
  pages =        "93--104",
  booktitle =    "Proceedings of Eurographics Workshop on Rendering 98",
  year =         1998,
  month =        june,
  conference =   "held in Vienna, Austria; 29 June - 1 July 1998",
  keywords =     "camera calibration, photographs, geometrical constraints,
  		  SVD, textures, filtering",
  url =          "http://www.iro.umontreal.ca/labs/infographie/papers/",
  abstract =     "We describe an \emph{interactive} system to reconstruct
  		  3D geometry and extract textures from a set of photographs
		  taken with arbitrary camera parameters. The basic idea is
		  to let the user draw 2D geometry on the images and set
		  constraints using these drawings.  Because the input comes
		  directly from the user, he can more easily resolve most of
		  the ambiguities and difficulties traditional computer
		  vision algorithms must deal with.

		  A set of geometrical linear constraints formulated as a
		  weighted least-squares problem is efficiently solved for
		  the camera parameters, and then for the 3D geometry.
		  Iterations between these two steps lead to improvements
		  on both results.  Once a satisfying 3D model is
		  reconstructed, its color textures are extracted by
		  sampling the projected texels in the corresponding images.
		  All the textures associated with a polygon are then fitted
		  to one another, and the corresponding colors are combined
		  according to a set of criteria in order to form a unique
		  texture.

		  The system produces 3D models and environments more
		  suitable for realistic image synthesis and computer
		  augmented reality.",
}

Project Page

Online Version