The Manhattan World Assumption: Regularities in Scene Statistics Which Enable Bayesian Inference

Abstract

Preliminary work by the authors made use of the so-called "Man(cid:173) hattan world" assumption about the scene statistics of city and indoor scenes. This assumption stated that such scenes were built on a cartesian grid which led to regularities in the image edge gra(cid:173) dient statistics. In this paper we explore the general applicability of this assumption and show that, surprisingly, it holds in a large variety of less structured environments including rural scenes. This enables us, from a single image, to determine the orientation of the viewer relative to the scene structure and also to detect target ob(cid:173) jects which are not aligned with the grid. These inferences are performed using a Bayesian model with probability distributions (e.g. on the image gradient statistics) learnt from real data.

Cite

Text

Coughlan and Yuille. "The Manhattan World Assumption: Regularities in Scene Statistics Which Enable Bayesian Inference." Neural Information Processing Systems, 2000.

Markdown

[Coughlan and Yuille. "The Manhattan World Assumption: Regularities in Scene Statistics Which Enable Bayesian Inference." Neural Information Processing Systems, 2000.](https://mlanthology.org/neurips/2000/coughlan2000neurips-manhattan/)

BibTeX

@inproceedings{coughlan2000neurips-manhattan,
  title     = {{The Manhattan World Assumption: Regularities in Scene Statistics Which Enable Bayesian Inference}},
  author    = {Coughlan, James M. and Yuille, Alan L.},
  booktitle = {Neural Information Processing Systems},
  year      = {2000},
  pages     = {845-851},
  url       = {https://mlanthology.org/neurips/2000/coughlan2000neurips-manhattan/}
}