Stages As Models of Scene Geometry V. Nedovic, A. W. M. Smeulders, A. Redert, J. M. Geusebroek In IEEE Transactions on Pattern Analysis and Machine Intelligence 2010. [bibtex] [pdf] [url]

Reconstruction of 3D scene geometry is an important element for scene understanding, autonomous vehicle and robot navigation, visual inspection and 3D television. We propose accounting for the inherent structure of the visual world when trying to solve the scene reconstruction problem. Consequently, we identify scene categorization as the first step towards robust and efficient depth estimation from single images. We introduce 15 typical 3D scene geometries called stages, each with a unique depth profile, which roughly correspond to a large majority of all images. Stage information serves as the first approximation of global depth, narrowing down the search space in depth estimation and object localization. We propose different sets of low-level features for depth estimation, and perform stage classification on two diverse datasets of television broadcasts. Classification results demonstrate that stages can be efficiently learned from low-dimensional image representations.

@Article{NedovicTPAMI2010,
  author       = "Nedovic, V. and Smeulders, A. W. M. and Redert, A. and Geusebroek, J. M.",
  title        = "Stages As Models of Scene Geometry",
  journal      = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
  number       = "9",
  volume       = "32",
  pages        = "1673--1687",
  year         = "2010",
  url          = "https://ivi.fnwi.uva.nl/isis/publications/2010/NedovicTPAMI2010",
  pdf          = "https://ivi.fnwi.uva.nl/isis/publications/2010/NedovicTPAMI2010/NedovicTPAMI2010.pdf",
  has_image    = 1
}