Manhattan World: Orientation and Outlier Detection by Bayesian Inference

  title={Manhattan World: Orientation and Outlier Detection by Bayesian Inference},
  author={James M. Coughlan and Alan L. Yuille},
  journal={Neural Computation},
This letter argues that many visual scenes are based on a Manhattan three-dimensional grid that imposes regularities on the image statistics. We construct a Bayesian model that implements this assumption and estimates the viewer orientation relative to the Manhattan grid. For many images, these estimates are good approximations to the viewer orientation (as estimated manually by the authors). These estimates also make it easy to detect outlier structures that are unaligned to the grid. To… CONTINUE READING

20 Figures & Tables



Citations per Year

130 Citations

Semantic Scholar estimates that this publication has 130 citations based on the available data.

See our FAQ for additional information.