Generic Scene Recovery using Multiple Images

In this paper, a generative model based method for recovering both the shape and the reflectance of the surface(s) of a scene from multiple images is presented, assuming that illumination conditions are known in advance. Based on a variational framework and via gradient descents, the algorithm minimizes simultaneously and consistently a global cost functional with respect to both shape and reflectance. Contrary to previous works which consider specific individual scenarios, our method applies to a number of scenarios -- mutiview stereovision, multiview photometric stereo, and multiview shape from shading. In addition, our approach naturally combines stereo, silhouette and shading cues in a single framework and, unlike most previous methods dealing with only Lambertian surfaces, the proposed method considers general dichromatic surfaces.

@InProceedings\{YPS09a,
  author       = "Yoon, Kuk-Jin and Prados, Emmanuel and Sturm, Peter",
  title        = "Generic Scene Recovery using Multiple Images",
  booktitle    = "SSVM'09 - 2nd International Conference on Scale Space and Variational Methods in Computer Vision",
  series       = "Lecture Notes in Computer Science series",
  month        = "jun",
  year         = "2009",
  editor       = "Springer",
  publisher    = "Springer",
  url          = "http://perception.inrialpes.fr/Publications/2009/YPS09a"
}